© 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. 131420
    Prev
    Next
    INDEX
    Explanations

    substantial experience

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

    money type or government

    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
    َب
    0.51
    ાલ
    0.47
     الاقوامی
    0.46
    ención
    0.46
    篪
    0.45
    攒
    0.45
     ocasión
    0.45
     Cerro
    0.44
    ércoles
    0.44
     percentile
    0.44
    POSITIVE LOGITS
    show
    0.58
    v
    0.57
    Phillips
    0.53
    Partners
    0.53
    in
    0.52
    F
    0.52
    worst
    0.51
    D
    0.51
    Show
    0.50
    Awards
    0.50
    Activations Density 0.000%

    No Known Activations