© 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. 103986
    Prev
    Next
    INDEX
    Explanations

    idioms and phrases

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

    programming, history, and specialized terminology

    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
     社
    0.49
     অন্য
    0.46
     純正
    0.43
    ыска
    0.42
     COND
    0.41
    URA
    0.40
     PERSONNEL
    0.40
    tbl
    0.39
     wij
    0.39
     },{
    0.39
    POSITIVE LOGITS
    เด
    0.52
     इश्क
    0.52
    ताएं
    0.50
    ទេ។
    0.49
     idios
    0.48
    嗥
    0.48
    چ
    0.47
    قول
    0.47
    ıdır
    0.46
    حال
    0.46
    Activations Density 0.001%

    No Known Activations