© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11715
    Prev
    Next
    INDEX
    Explanations

    give you/me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﺭ
    2.90
    ﺩ
    2.74
    ITY
    2.68
    izing
    2.64
    ity
    2.64
    ы
    2.64
    ﺵ
    2.63
     punt
    2.55
    ש
    2.54
    chunk
    2.52
    POSITIVE LOGITS
    e
    2.93
    UIAlert
    2.85
    x
    2.78
    Lah
    2.78
    tiered
    2.75
    ष
    2.73
    Regards
    2.70
    ு
    2.69
    ٰ
    2.68
    eis
    2.66
    Activations Density 0.045%

    No Known Activations