© 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. 183188
    Prev
    Next
    INDEX
    Explanations

    Sponsor Saturday minute producing loss

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

    sizes, ways, educational, playfully

    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
    paragraphs
    0.50
    𒍣
    0.49
    แตก
    0.48
    开头
    0.46
    ┆
    0.46
    Ruby
    0.45
    ুল্লাহ
    0.45
    テキスト
    0.45
    gettags
    0.45
    侗
    0.44
    POSITIVE LOGITS
     límite
    0.49
     quir
    0.47
     bởi
    0.45
     kämp
    0.44
     satta
    0.43
     riego
    0.43
     meist
    0.43
     nü
    0.43
     alun
    0.43
     nhờ
    0.42
    Activations Density 0.001%

    No Known Activations