© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116312
    Prev
    Next
    INDEX
    Explanations

    on duty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erts
    -0.79
    Stéphane
    -0.77
    rogates
    -0.73
    caret
    -0.71
     저장
    -0.71
    ูป
    -0.70
    interceptors
    -0.70
    acu
    -0.70
     méthode
    -0.69
    mbito
    -0.69
    POSITIVE LOGITS
     duty
    4.31
     duties
    3.52
    duty
    3.27
    Duty
    2.80
     Duty
    2.66
     DUTY
    2.58
     Duties
    2.22
    Duties
    1.85
     assignment
    1.63
    DUT
    1.54
    Activations Density 0.025%

    No Known Activations