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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 185
    Prev
    Next
    INDEX
    Explanations

    Evidence

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @theofarrell99

    numbers and mathematical operators in a computational context.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @theofarrell99

    mathematical formulas, code structures, and technical problem-solving content.

    oai_token-act-pair · claude-4-5-haikuTriggered by @theofarrell99

    Evidence

    np_max-act-logits · claude-4-5-haikuTriggered by @theofarrell99
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    •rel comp
    cand 1 (high max. kl in multiple examples)

    No Comments

    Negative Logits
    arp
    1.31
     Alek
    1.29
     Haller
    1.23
     alm
    1.23
    ₁,
    1.23
     Grig
    1.18
     faucets
    1.18
     bathrooms
    1.17
    oglobulin
    1.16
    properties
    1.15
    POSITIVE LOGITS
     Evidence
    0.62
     evidence
    0.60
     revue
    0.54
     she
    0.54
     She
    0.52
     indu
    0.50
     siger
    0.49
    様子
    0.49
     veck
    0.47
    Evidence
    0.47
    Activations Density 2.870%

    No Known Activations