© 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-16K
    7. 13204
    Prev
    Next
    INDEX
    Explanations

    peak, limits, and extremes

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

    lowest or highest point

    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_16k_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
    Includes
    0.42
    ونية
    0.42
    酺
    0.41
     Tubes
    0.41
     учреждения
    0.41
     başlad
    0.40
    যু
    0.40
     droits
    0.40
     pasos
    0.40
     comprensión
    0.40
    POSITIVE LOGITS
     peak
    0.87
    peak
    0.78
    峰
    0.73
     Peak
    0.72
    Peak
    0.66
     point
    0.64
    ピーク
    0.64
     lowest
    0.62
     POINT
    0.61
     вершины
    0.60
    Activations Density 0.443%

    No Known Activations