© 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. 170058
    Prev
    Next
    INDEX
    Explanations

    collection –—

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

    OpenAPI specification, elegance and

    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
    ุ
    0.54
    ভৃতি
    0.54
    Diary
    0.51
    Todas
    0.50
    DatePicker
    0.50
    ן
    0.48
    mDatas
    0.47
    щает
    0.46
     מ
    0.46
    På
    0.45
    POSITIVE LOGITS
    locks
    0.47
    釋
    0.44
    shiro
    0.42
     mene
    0.42
     perror
    0.42
     endIndex
    0.42
    是因為
    0.41
     ⭐
    0.40
     Закон
    0.40
     "$
    0.40
    Activations Density 0.001%

    No Known Activations