© 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. 109503
    Prev
    Next
    INDEX
    Explanations

    email, fee, contact, dissolving, mysterious

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

    General Purpose Chatbots

    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
    C
    0.61
    Centre
    0.55
    ast
    0.51
    G
    0.51
    un
    0.50
    S
    0.49
    am
    0.49
    over
    0.49
    an
    0.49
    D
    0.49
    POSITIVE LOGITS
    したり
    0.53
     وقتی
    0.52
     جاي
    0.52
     ホ
    0.51
     系列
    0.51
     auß
    0.50
    秘书
    0.50
     非常
    0.49
    writeFileSync
    0.48
     زمانے
    0.48
    Activations Density 0.001%

    No Known Activations