© 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. 2522
    Prev
    Next
    INDEX
    Explanations

    document structure and organization

    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
    0.62
    entire
    0.55
    io
    0.53
    first
    0.52
     E
    0.52
    antlr
    0.51
    fd
    0.50
    {
    0.50
    alt
    0.50
    ip
    0.49
    POSITIVE LOGITS
     або
    0.51
     наблю
    0.49
     nourrice
    0.48
     utilis
    0.48
     või
    0.47
    の使用
    0.47
     grosseur
    0.47
     biologie
    0.46
    Ტ
    0.46
     mož
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.