© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 245004
    Prev
    Next
    INDEX
    Explanations

    outlook, familiar, witnesses, cheese

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    0.61
    if
    0.55
    ang
    0.55
    com
    0.53
    lam
    0.52
    ap
    0.51
    é
    0.51
    <start_of_image>
    0.51
    wa
    0.50
    </strong>
    0.49
    POSITIVE LOGITS
    MSFont
    0.60
    斯特
    0.55
    淉
    0.51
    स्टर
    0.51
     popOperand
    0.51
    樍
    0.51
     arxivləşdirilib
    0.50
     mayam
    0.50
     جميعا
    0.49
     тыс
    0.49
    Activations Density 0.000%

    No Known Activations