© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221418
    Prev
    Next
    INDEX
    Explanations

    native language punctuation

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

    days of the week

    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
     لأنه
    0.49
    숏
    0.46
     vutta
    0.46
    toBytes
    0.46
     pretože
    0.45
    SwapChain
    0.45
     दशकों
    0.45
    㺪
    0.45
     Hurt
    0.44
    托管
    0.44
    POSITIVE LOGITS
    原
    0.49
    Hiện
    0.47
    チ
    0.47
    <0x80>
    0.44
    秋
    0.44
    八
    0.43
    景
    0.42
    AS
    0.42
    RI
    0.41
    利
    0.41
    Activations Density 0.000%

    No Known Activations