© 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. 98584
    Prev
    Next
    INDEX
    Explanations

    local host

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

    Ends Tonight

    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
    0.56
    );
    0.56
    al
    0.52
    entity
    0.52
    i
    0.50
    ;
    0.48
    ->
    0.48
    Entity
    0.47
    ente
    0.47
     Theology
    0.47
    POSITIVE LOGITS
    欒
    0.58
    Ꮔ
    0.57
    зін
    0.54
    ድግዳ
    0.50
    пону
    0.50
     proportionately
    0.49
    นาม
    0.49
    綰
    0.49
    мс
    0.48
    飲食店
    0.48
    Activations Density 0.000%

    No Known Activations