© 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. 258035
    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
    ar
    0.60
    as
    0.60
    z
    0.58
    in
    0.58
    im
    0.56
    ag
    0.55
    का
    0.54
    ex
    0.54
    are
    0.54
    and
    0.54
    POSITIVE LOGITS
     IncludeField
    0.57
    IsResolver
    0.55
     IntegerValue
    0.54
     വിദ്യാഭ്യാസ
    0.53
     Enseñanza
    0.53
     教え
    0.52
     Heisenberg
    0.52
     הור
    0.52
     التعليم
    0.51
     願い
    0.51
    Activations Density 0.002%

    No Known Activations