© 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. 168962
    Prev
    Next
    INDEX
    Explanations

    placeholder page visiting

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

    questions and answers

    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
    ણ
    0.55
    ;|
    0.53
    ősz
    0.53
    .[[
    0.51
     الجيش
    0.49
    疥
    0.49
    ত্বের
    0.48
    .‏
    0.48
    訫
    0.48
    oxyd
    0.47
    POSITIVE LOGITS
     commuting
    0.48
     borrar
    0.47
     connecting
    0.46
     STP
    0.44
     strategic
    0.44
     drawer
    0.43
     handout
    0.43
     guidebook
    0.41
     scoring
    0.41
     Rae
    0.41
    Activations Density 0.001%

    No Known Activations