© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30975
    Prev
    Next
    INDEX
    Explanations

    captions and analysis sections

    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
     schedule
    -0.77
    Scheduling
    -0.76
    vst
    -0.74
    SCHED
    -0.74
     Scheduling
    -0.73
    давно
    -0.72
     температуре
    -0.72
    🍘
    -0.71
     μην
    -0.71
     Schedule
    -0.71
    POSITIVE LOGITS
     cropped
    0.98
     cropping
    0.82
     круп
    0.80
    兪
    0.78
     TURN
    0.76
     orig
    0.75
     Stew
    0.75
    sulf
    0.73
     thumbnail
    0.73
    arde
    0.73
    Activations Density 0.003%

    No Known Activations