© 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. 14575
    Prev
    Next
    INDEX
    Explanations

    child's actions and possessions

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

    childhood names and scenarios

    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
    र्चे
    0.46
     स्था
    0.46
     Букмекер
    0.44
    誡
    0.43
    性感
    0.42
    зму
    0.42
    employees
    0.42
    strtotime
    0.41
    भोग
    0.41
    健身
    0.41
    POSITIVE LOGITS
     어린이
    0.95
     کودک
    0.90
     الطفل
    0.89
    🧒
    0.88
     শিশু
    0.86
     preschool
    0.86
     बच्ची
    0.85
     الأطفال
    0.84
     niño
    0.83
     criança
    0.82
    Activations Density 0.213%

    No Known Activations