© 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. 102871
    Prev
    Next
    INDEX
    Explanations

    academic and professional requirements

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

    search to check availability

    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
    Η
    0.47
    IENTO
    0.47
    ध्ये
    0.47
    Colors
    0.47
    Phe
    0.46
    Pages
    0.46
    Chronic
    0.46
    Offset
    0.45
    5
    0.45
    Pictures
    0.45
    POSITIVE LOGITS
    си
    0.54
    ти
    0.47
     Дон
    0.47
    лося
    0.46
    ープ
    0.46
     Нико
    0.44
    ci
    0.44
    nite
    0.42
    вим
    0.42
    ви
    0.42
    Activations Density 0.001%

    No Known Activations