© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 256527
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     spôsob
    0.55
     způsob
    0.48
     Godfather
    0.48
    ே
    0.47
     Tento
    0.46
     nebo
    0.45
    ptitle
    0.45
     hè
    0.44
     FOR
    0.44
     Englishmen
    0.44
    POSITIVE LOGITS
     कन्
    0.62
     간
    0.49
     automática
    0.45
    ाम
    0.45
    टेन
    0.44
    AccessException
    0.43
    🔒
    0.42
    кон
    0.42
    ब्र
    0.41
    TAC
    0.41
    Activations Density 0.001%

    No Known Activations