© 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. 45650
    Prev
    Next
    INDEX
    Explanations

    connection and calls

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

    connection pool

    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
    WindowClass
    0.49
     ملف
    0.48
     wyra
    0.48
     كتب
    0.47
    文件
    0.46
     Lobkovic
    0.46
     sichtbar
    0.46
     artyku
    0.45
    FileType
    0.45
    POSITIVE LOGITS
     and
    0.52
     AND
    0.51
     &
    0.45
    microsoft
    0.43
    fest
    0.43
    했고
    0.42
    बोर्ड
    0.42
     andRow
    0.41
    まれ
    0.41
     slipping
    0.41
    Activations Density 0.000%

    No Known Activations