© 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. 197709
    Prev
    Next
    INDEX
    Explanations

    account, review, link, instance

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

    left or right padding

    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
    if
    0.64
    ↵
    0.57
    width
    0.57
    it
    0.55
    re
    0.52
    x
    0.52
     flatten
    0.52
    error
    0.52
     parentheses
    0.52
     flattened
    0.51
    POSITIVE LOGITS
    墀
    0.65
    鳧
    0.59
     Сасик
    0.55
    舢
    0.54
    罵
    0.54
    营养
    0.52
    CHRIST
    0.52
    禛
    0.52
     tắm
    0.52
    聋
    0.52
    Activations Density 0.000%

    No Known Activations