© 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. 88319
    Prev
    Next
    INDEX
    Explanations

    food and shopping contexts

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

    challenges and emotional distress

    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
    ۲
    0.45
     ކުރ
    0.44
     바로
    0.43
    ۴
    0.43
     Paints
    0.42
     ಹೆಚ್ಚು
    0.42
    pares
    0.40
    apons
    0.40
     económ
    0.40
     conduits
    0.40
    POSITIVE LOGITS
    鲑
    0.50
    あ
    0.50
    Το
    0.48
    সমা
    0.47
     teplot
    0.47
     BOY
    0.46
     tepl
    0.46
    鏂
    0.45
    ที่
    0.45
    忤
    0.45
    Activations Density 0.001%

    No Known Activations