© 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. 104632
    Prev
    Next
    INDEX
    Explanations

    provinces surrounding, teddy bears, gel implants

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

    access to code or content

    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
    crawler
    0.56
    ミラー
    0.50
    rawl
    0.50
    t
    0.49
    (
    0.49
    extends
    0.48
    :...
    0.48
    discover
    0.47
    lowercase
    0.47
    :{
    0.45
    POSITIVE LOGITS
     इक्वेशन
    0.46
     కా
    0.45
     यश
    0.44
     друз
    0.44
     Year
    0.43
     еще
    0.43
     Ka
    0.43
     भाइयों
    0.42
    कर्ताओं
    0.42
     Elizabeth
    0.42
    Activations Density 0.000%

    No Known Activations