© 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. 164624
    Prev
    Next
    INDEX
    Explanations

    categorization and related concepts

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

    creeping/crept across or onto

    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
     Deepika
    0.45
    ციის
    0.44
    仇
    0.44
     Atra
    0.42
    郤
    0.42
     Eshelby
    0.42
    ოლი
    0.41
     निशा
    0.41
    SearchCV
    0.41
    LessThan
    0.41
    POSITIVE LOGITS
     airlines
    0.48
     dates
    0.46
     presentamos
    0.46
    ^{*}+
    0.45
     পরিণত
    0.45
     lanza
    0.44
     পরের
    0.44
     nazionale
    0.44
     paci
    0.43
    شته
    0.43
    Activations Density 0.001%

    No Known Activations