© 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. 218913
    Prev
    Next
    INDEX
    Explanations

    transition phrases and specific contexts

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

    funny tickets and insurance

    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
     dirname
    0.49
     tình
    0.49
     paral
    0.48
    郡
    0.46
     multiplica
    0.46
    പ്പറ
    0.45
    ционе
    0.45
     provincia
    0.43
    ргани
    0.43
     audioElement
    0.43
    POSITIVE LOGITS
     ۸
    0.54
    at
    0.50
     Κα
    0.48
    ar
    0.48
     بود
    0.48
    wood
    0.48
    er
    0.47
     ۶
    0.46
    batter
    0.46
     بودند
    0.46
    Activations Density 0.000%

    No Known Activations