© 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. 244114
    Prev
    Next
    INDEX
    Explanations

    legislative or legal context

    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
    :
    0.47
    Austin
    0.46
    Z
    0.46
    Indianapolis
    0.45
    @
    0.45
    Flam
    0.44
     Correa
    0.44
     (
    0.42
    Bz
    0.42
    ную
    0.42
    POSITIVE LOGITS
    પૂર્ણ
    0.53
     arka
    0.52
     ܐ
    0.52
     რომელიც
    0.52
     리그
    0.52
    𒃶
    0.51
     દવા
    0.51
     රස
    0.50
     bởi
    0.50
    ulasi
    0.49
    Activations Density 0.000%

    No Known Activations