© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27362
    Prev
    Next
    INDEX
    Explanations

    time in months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    적이
    0.38
    盐
    0.38
    作
    0.38
    michael
    0.37
     मूर्
    0.37
    refs
    0.36
    数十
    0.36
    发
    0.36
    ish
    0.35
    isna
    0.35
    POSITIVE LOGITS
     months
    0.89
     месяцев
    0.81
    개월
    0.77
    months
    0.77
     Months
    0.76
     Monate
    0.76
     maanden
    0.73
     miesięcy
    0.71
     mån
    0.69
    month
    0.68
    Activations Density 0.009%

    No Known Activations