© 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. 251596
    Prev
    Next
    INDEX
    Explanations

    lists, punctuation, and pauses

    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
     Giri
    0.48
     baile
    0.47
     simple
    0.46
    ﺌ
    0.46
     কাউকে
    0.46
     coffee
    0.45
     بہترین
    0.44
     Girona
    0.43
     presentazione
    0.43
     refueling
    0.43
    POSITIVE LOGITS
    根據
    0.50
    isch
    0.49
    ,}
    0.48
    asonic
    0.43
    CrL
    0.42
    utlich
    0.42
    ashington
    0.42
     щодо
    0.41
    ich
    0.41
    科技
    0.41
    Activations Density 0.001%

    No Known Activations