© 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. 191024
    Prev
    Next
    INDEX
    Explanations

    restaurant, chapter, subsequently came

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

    kingdom, Api, libraries, setting

    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
    Nel
    0.49
    尼
    0.49
    Nell
    0.47
    ئ
    0.47
    ئين
    0.46
    經常
    0.45
    Institutional
    0.45
    MessageType
    0.44
    Instit
    0.44
    苚
    0.44
    POSITIVE LOGITS
    respons
    0.52
    ínguez
    0.49
     침
    0.49
    エンド
    0.48
    トーク
    0.47
    respon
    0.46
     immunosupp
    0.46
    ibur
    0.46
     Mediterranean
    0.45
    ayı
    0.44
    Activations Density 0.001%

    No Known Activations