© 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. 66204
    Prev
    Next
    INDEX
    Explanations

    weekend warrior

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

    Clear phrases

    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
    ASE
    0.45
    me
    0.45
    ENTE
    0.44
    SE
    0.43
     traverses
    0.43
    Ả
    0.42
    <start_of_image>
    0.42
    ACH
    0.41
    Dreams
    0.41
    cheese
    0.40
    POSITIVE LOGITS
    δήποτε
    0.52
     కారణంగా
    0.52
     വി
    0.51
     می‌ده
    0.50
    缺少
    0.50
    များနှင့်
    0.49
     لري
    0.48
     می‌دهد
    0.48
     ኤ
    0.48
     φα
    0.48
    Activations Density 0.000%

    No Known Activations