© 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. 222320
    Prev
    Next
    INDEX
    Explanations

    about purchase

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

    foreign languages or specific words

    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
    据
    0.49
     sniping
    0.48
    니다
    0.47
    蕗
    0.46
     blasted
    0.46
    ლებელია
    0.45
    $$
    0.45
    Wide
    0.44
    ッチ
    0.43
    ススメ
    0.43
    POSITIVE LOGITS
     комфор
    0.43
    стьян
    0.43
     Ost
    0.43
     perde
    0.43
     ermöglicht
    0.42
     wenn
    0.42
    стен
    0.42
     doulou
    0.42
     testament
    0.41
    )}}{
    0.41
    Activations Density 0.000%

    No Known Activations