© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8024
    Prev
    Next
    INDEX
    Explanations

    update, message, data, w

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     비슷한
    1.05
     mát
    1.02
     inform
    1.01
     particip
    1.00
    e
    1.00
     året
    0.99
     제주
    0.98
     apparatus
    0.98
     solit
    0.97
     recompens
    0.96
    POSITIVE LOGITS
    Draw
    1.42
    draw
    1.35
     SqlCommand
    1.35
    Understanding
    1.34
    ٺ
    1.33
    shown
    1.30
    ⇉
    1.30
    仼
    1.28
     Transcript
    1.28
     डेफिनेशन
    1.28
    Activations Density 0.000%

    No Known Activations