© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13453
    Prev
    Next
    INDEX
    Explanations

    cocktail enthusiasts

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of technical numeric specifications and model‐style codes (e.g. measurements, part numbers, alphanumeric product identifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical or product specifications, particularly measurements and part numbers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    technical automotive and powersports drivetrain/engine content, especially detailed specs, components, and installation or break‑in discussions for shafts, joints, mounts, and related hardware

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     samoglas
    1.06
     chatbots
    1.06
    addena
    1.05
     kosakata
    1.04
     मानवीय
    1.03
    élène
    1.03
    ayeva
    1.02
     powodu
    1.01
     católica
    1.00
     मानवता
    1.00
    POSITIVE LOGITS
     enduro
    1.20
     drivetrain
    1.19
    1
    1.16
     aftermarket
    1.15
     torque
    1.13
     camo
    1.13
     bushings
    1.09
     Torque
    1.04
     specs
    1.03
     Camaro
    1.03
    Activations Density 0.607%

    No Known Activations