© 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. 23344
    Prev
    Next
    INDEX
    Explanations

    float and real numbers

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

    floating-point numbers

    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
     रणनी
    0.59
     경찰
    0.56
    仓库
    0.56
     ಬಿಜೆಪಿ
    0.55
    博物馆
    0.54
     кирпи
    0.54
     भाजप
    0.54
    隧
    0.54
    党员
    0.54
     організа
    0.53
    POSITIVE LOGITS
     parseFloat
    1.16
     float
    1.11
     floating
    1.00
     Float
    1.00
     floats
    0.97
    float
    0.96
     FLOAT
    0.95
    parseFloat
    0.94
    SetFloat
    0.93
     decimal
    0.91
    Activations Density 0.006%

    No Known Activations