© 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. 6689
    Prev
    Next
    INDEX
    Explanations

    WITHOUT WARRANTY

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

    does not constitute medical advice

    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
    ayeva
    0.38
     આવા
    0.37
    anesu
    0.36
    imgInit
    0.34
    欵
    0.33
    তনা
    0.33
    ೆಂದು
    0.33
     बिकॉज
    0.33
    দূত
    0.33
    របស់យើង
    0.32
    POSITIVE LOGITS
    -
    0.39
     to
    0.35
     it
    0.34
     sist
    0.34
     canad
    0.34
     =
    0.33
     magazine
    0.32
    առ
    0.31
     att
    0.30
     ré
    0.30
    Activations Density 0.400%

    No Known Activations