© 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. 78319
    Prev
    Next
    INDEX
    Explanations

    program, frequency, your

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

    mechanism driving

    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
    adrat
    0.48
    mero
    0.48
    /
    0.47
    iqu
    0.46
    ydro
    0.45
    ifu
    0.45
    apopt
    0.45
     invaders
    0.44
    ograms
    0.43
    iquer
    0.43
    POSITIVE LOGITS
    達
    0.48
     ня
    0.47
     років
    0.46
     হতাশ
    0.45
     উৎসাহ
    0.45
    ണി
    0.44
     بيان
    0.44
     svět
    0.44
    ონ
    0.43
    と呼ばれる
    0.43
    Activations Density 0.000%

    No Known Activations