© 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. 239542
    Prev
    Next
    INDEX
    Explanations

    consultation, & are, similar, begins, precision

    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
    ك
    0.55
    Muc
    0.49
    Bind
    0.49
    ANE
    0.47
    Array
    0.47
    c
    0.47
     Bind
    0.46
    库
    0.46
     K
    0.45
     ভিত্তি
    0.44
    POSITIVE LOGITS
     twenties
    0.56
     salaried
    0.52
    🤳
    0.52
     purse
    0.50
     relentless
    0.49
     watchlist
    0.49
    ेंद
    0.49
    🏿
    0.49
    🙋
    0.48
     bullish
    0.48
    Activations Density 0.000%

    No Known Activations