© 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. 164820
    Prev
    Next
    INDEX
    Explanations

    by quoting, wrong guy, proven innocent

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

    foreign languages and scores

    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
     metà
    0.48
    毀
    0.48
    傑
    0.47
     Küh
    0.45
    ᾳ
    0.45
    անակ
    0.44
    精
    0.44
    __
    0.43
    高く
    0.43
    гово
    0.43
    POSITIVE LOGITS
     spans
    0.48
    ldon
    0.47
    sellers
    0.46
    sk
    0.45
    to
    0.44
    isches
    0.43
    城乡
    0.43
     ouder
    0.43
    ollar
    0.43
     source
    0.42
    Activations Density 0.001%

    No Known Activations