© 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. 206228
    Prev
    Next
    INDEX
    Explanations

    records with

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

    history, people, and buy

    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
    sprechend
    0.53
    t
    0.50
     დროს
    0.48
    antemente
    0.47
     टेक्नोलॉजी
    0.47
     ممال
    0.46
    DSM
    0.46
     nombrado
    0.46
     জ্ঞানী
    0.45
     Manch
    0.44
    POSITIVE LOGITS
    getHours
    0.43
    чники
    0.43
     contaminated
    0.43
    шибка
    0.40
    炖
    0.40
    里面的
    0.39
    臨時
    0.39
    Both
    0.39
    ్రహ
    0.39
    માં
    0.38
    Activations Density 0.001%

    No Known Activations