© 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. 115903
    Prev
    Next
    INDEX
    Explanations

    locations followed by state abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite

    input() with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    inata
    0.48
    damaged
    0.47
    mette
    0.47
    reduced
    0.46
    못
    0.46
    mangle
    0.44
    legten
    0.44
    rectionType
    0.44
    பந்த
    0.43
    なりません
    0.43
    POSITIVE LOGITS
     นี่
    0.54
    ;
    0.52
     indust
    0.50
    ;|
    0.50
     giveaways
    0.50
     tiende
    0.50
     t
    0.48
    ;<
    0.48
     <
    0.48
    u
    0.47
    Activations Density 0.002%

    No Known Activations