© 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. 117900
    Prev
    Next
    INDEX
    Explanations

    vendor agrees

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

    goals, purpose, information

    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
    י
    0.52
    i
    0.50
    스
    0.49
     Ghosh
    0.48
    ฺ
    0.48
    т
    0.47
    м
    0.47
    *
    0.47
    ்டர்
    0.46
    は
    0.46
    POSITIVE LOGITS
    ivert
    0.49
     داده
    0.46
     بلوچستان
    0.44
     bâtiment
    0.44
     ترکیب
    0.43
     تنگ
    0.42
     jouent
    0.42
     realizado
    0.42
     واکنش
    0.41
    SqlClient
    0.41
    Activations Density 0.000%

    No Known Activations