© 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. 86254
    Prev
    Next
    INDEX
    Explanations

    Book online and compare discount rates

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

    technical frameworks

    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
    ρωση
    0.52
    ন
    0.46
    omorphisms
    0.44
    खाना
    0.43
    нский
    0.43
    ництво
    0.43
     нала
    0.42
    SAND
    0.42
    い
    0.42
     hybridized
    0.41
    POSITIVE LOGITS
     detal
    0.54
     meinem
    0.53
     ذه
    0.48
     تحتوي
    0.48
    PanelVisual
    0.46
    nega
    0.46
    ية
    0.46
     ذا
    0.46
    ামুটি
    0.46
    refer
    0.46
    Activations Density 0.000%

    No Known Activations