© 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. 37205
    Prev
    Next
    INDEX
    Explanations

    course names and levels

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

    Statistics, probability, data analysis

    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
    ፣
    0.39
    jamin
    0.38
     eer
    0.37
    好事
    0.37
    بوب
    0.37
     someday
    0.36
    等你
    0.36
     solidar
    0.36
     sats
    0.36
     وليس
    0.35
    POSITIVE LOGITS
     Конгрегация
    0.41
     পরিবার
    0.39
    ᴇ
    0.38
    ikalische
    0.37
     используется
    0.37
     городе
    0.37
     ребенок
    0.37
     कुटुंबा
    0.37
     aquifer
    0.37
     Kindern
    0.37
    Activations Density 0.001%

    No Known Activations