© 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. 169572
    Prev
    Next
    INDEX
    Explanations

    basis behind, Road after, era of

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

    properties of velocity

    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
    <strong>
    0.52
    {
    0.49
    <
    0.49
    !
    0.48
     doar
    0.46
     lakini
    0.46
    :
    0.46
    amp
    0.45
    ↵↵↵↵
    0.45
    POSITIVE LOGITS
    蚣
    0.51
     부정
    0.48
    мати
    0.48
    Aggregation
    0.48
     изображение
    0.46
     해결
    0.46
    <unused626>
    0.46
     ভুট্টোর
    0.46
    <unused2132>
    0.46
    hydrocèle
    0.46
    Activations Density 0.002%

    No Known Activations