© 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. 108970
    Prev
    Next
    INDEX
    Explanations

    financial transactions or items

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

    assessments and requirements

    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
    ursos
    0.45
    ichting
    0.44
    ampi
    0.43
    Los
    0.43
    ordering
    0.43
     दवाओं
    0.43
    存
    0.41
     sistemas
    0.41
    芰
    0.41
    性
    0.40
    POSITIVE LOGITS
     Wię
    0.52
    জ
    0.47
     đường
    0.47
     prawidł
    0.46
     aldı
    0.46
     chuyển
    0.45
     Đường
    0.45
     olímp
    0.45
     Gewicht
    0.43
     الاعدادي
    0.43
    Activations Density 0.000%

    No Known Activations