© 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. 102432
    Prev
    Next
    INDEX
    Explanations

    following certain phrases

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

    bank account

    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
     historical
    0.46
     تنظیم
    0.42
    settings
    0.42
     تاریخی
    0.40
    牧
    0.39
    中国
    0.39
     бого
    0.38
    angsa
    0.38
     tahun
    0.38
     Historical
    0.38
    POSITIVE LOGITS
    חס
    0.55
    妳
    0.52
     మీరు
    0.52
    比如說
    0.50
    럏
    0.49
    $+
    0.49
    UPLOAD
    0.49
     لذلك
    0.49
     $+
    0.48
     زائدا
    0.48
    Activations Density 0.001%

    No Known Activations