© 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. 191717
    Prev
    Next
    INDEX
    Explanations

    words after punctuation

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

    individual development

    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
    *,
    0.52
     Старки
    0.49
    ;,
    0.46
    ,…
    0.45
    *;
    0.43
    чү
    0.43
    +,
    0.42
    <0x87>
    0.42
    북도
    0.41
    ;
    0.41
    POSITIVE LOGITS
     plais
    0.48
     délais
    0.47
    anye
    0.46
    oy
    0.46
    ח
    0.46
    elight
    0.45
    les
    0.45
    ávy
    0.45
     দাবী
    0.45
    áct
    0.44
    Activations Density 0.003%

    No Known Activations