© 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. 77384
    Prev
    Next
    INDEX
    Explanations

    light modes and settings

    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
    wartz
    -0.75
     DELLE
    -0.74
     cholesterol
    -0.71
    モニター
    -0.71
    加熱
    -0.69
    ።
    -0.69
    姞
    -0.69
    介入
    -0.69
    addGap
    -0.68
    ARROLLO
    -0.68
    POSITIVE LOGITS
     headband
    0.93
     beam
    0.90
    FundMe
    0.89
    runtime
    0.86
     NATO
    0.85
     runtime
    0.82
     modes
    0.82
     burn
    0.82
     SOS
    0.82
     brightness
    0.79
    Activations Density 0.004%

    No Known Activations