© 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. 256867
    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
     stars
    0.46
    că
    0.46
    ç
    0.45
    ’
    0.45
    uç
    0.45
    ü
    0.44
    k
    0.44
     ram
    0.44
     simulated
    0.44
     odor
    0.44
    POSITIVE LOGITS
    憋
    0.57
    汨
    0.52
     квадра
    0.52
    篮球
    0.50
    竦
    0.50
     сфор
    0.50
     уравнения
    0.49
     мисте
    0.49
    翕
    0.49
     मैथ्स
    0.49
    Activations Density 0.001%

    No Known Activations