© 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. 42370
    Prev
    Next
    INDEX
    Explanations

    increase by numbers

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

    concept or role

    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
    ayın
    0.52
     testamentary
    0.50
    $.
    0.48
     بشأن
    0.48
    oren
    0.47
     domeni
    0.46
    okra
    0.46
     بارے
    0.46
     ums
    0.46
    toothbrush
    0.45
    POSITIVE LOGITS
    ここまで
    0.45
     ক্র
    0.45
     suffers
    0.42
     grows
    0.42
     crescita
    0.42
    迳
    0.42
     knob
    0.41
     تكبرها
    0.40
     GROW
    0.40
    ேச
    0.39
    Activations Density 0.000%

    No Known Activations