© 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. 257292
    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
     tacky
    0.48
    Didn
    0.48
     Section
    0.46
    ډ
    0.45
     Didn
    0.45
     crème
    0.44
    MD
    0.44
    I
    0.44
     bowlers
    0.44
    MJ
    0.43
    POSITIVE LOGITS
    मंत्र
    0.48
     restantes
    0.46
     अनलॉक
    0.46
     tiempo
    0.45
     대해
    0.43
     publie
    0.43
     desapare
    0.43
     veces
    0.42
     সময়ে
    0.42
     subgoal
    0.42
    Activations Density 0.001%

    No Known Activations