© 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. 79278
    Prev
    Next
    INDEX
    Explanations

    script execution

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

    errors or status

    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
     Erlebnis
    0.44
     당시
    0.42
    slüman
    0.40
     Anywhere
    0.40
    ｍ
    0.40
     damal
    0.40
     ಅದು
    0.40
     damals
    0.39
    ん
    0.39
     مرحوم
    0.39
    POSITIVE LOGITS
    forEach
    0.54
    setConfig
    0.47
     establishes
    0.46
    setBackground
    0.45
    setFont
    0.44
    setAttribute
    0.44
    setStyleSheet
    0.44
    print
    0.43
    ्रीट
    0.43
     populate
    0.43
    Activations Density 0.003%

    No Known Activations