© 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. 253864
    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
    arente
    0.49
    нему
    0.46
    我们
    0.44
     вед
    0.44
    künd
    0.43
     dejamos
    0.43
    溥
    0.43
     olmadan
    0.43
    충
    0.43
    чего
    0.42
    POSITIVE LOGITS
    orse
    0.51
    ie
    0.49
    at
    0.49
     শব্দ
    0.48
     ମ
    0.48
    ية
    0.47
    wristwatch
    0.47
    戦略
    0.47
     ഗവേഷ
    0.46
    ार्मिक
    0.46
    Activations Density 0.001%

    No Known Activations