© 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. 48152
    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
     Watching
    0.43
     जबरदस्त
    0.40
     толькі
    0.39
    Budget
    0.39
    ","
    0.39
    페이지
    0.39
    有
    0.38
    页面
    0.38
    实的
    0.38
    耸
    0.38
    POSITIVE LOGITS
    resistant
    0.49
    pano
    0.47
     cot
    0.47
     conoc
    0.47
     arbre
    0.47
     esposo
    0.47
     zou
    0.46
     médecine
    0.46
     believers
    0.46
     animale
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.