© 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. 26649
    Prev
    Next
    INDEX
    Explanations

    possessives and of

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

    subscripts and powers

    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
     of
    0.69
    いて
    0.69
    נ
    0.69
    ב
    0.68
    מ
    0.68
    خرى
    0.67
    صر
    0.64
    ，
    0.63
    ם
    0.63
    لی
    0.62
    POSITIVE LOGITS
    ut
    0.69
    é
    0.69
    is
    0.67
    oo
    0.66
    ir
    0.66
    ha
    0.65
    ib
    0.64
     first
    0.63
    in
    0.63
     پہلی
    0.62
    Activations Density 0.000%

    No Known Activations