© 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. 74899
    Prev
    Next
    INDEX
    Explanations

    providing, baby, warmer, children

    np_acts-logits-general · gemini-2.5-flash-lite

    powering things

    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
    Nb
    0.48
    ।
    0.48
     Ada
    0.47
     dating
    0.46
     Iz
    0.45
     Gyan
    0.45
     a
    0.44
    ﺒ
    0.44
     continuation
    0.43
     modulation
    0.43
    POSITIVE LOGITS
     ट्रे
    0.48
    ワゴン
    0.44
    谁
    0.44
    全球
    0.43
    री
    0.42
    商城
    0.42
    选取
    0.42
     जवळ
    0.41
    windigkeit
    0.41
     tokom
    0.41
    Activations Density 0.002%

    No Known Activations