© 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. 207951
    Prev
    Next
    INDEX
    Explanations

    organization, often, dive, Bay

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

    hashtags and related phrases

    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
    Negative Logits
    i
    0.57
    ｐ
    0.50
    ي
    0.47
    ＮＡ
    0.46
    ０
    0.46
    ड
    0.45
     ró
    0.45
    UNIT
    0.44
    Criterion
    0.44
     аэро
    0.44
    POSITIVE LOGITS
    全新的
    0.49
    淦
    0.48
    ảy
    0.48
     नाखूनों
    0.45
     तेज
    0.45
    を担当
    0.43
    崭
    0.43
    間違
    0.43
     참고
    0.43
     McInt
    0.42
    Activations Density 0.003%

    No Known Activations