© 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. 10-GEMMASCOPE-RES-131K
    7. 101196
    Prev
    Next
    INDEX
    Explanations

    reckless driving or conduct

    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_10/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
    饧
    -2.39
     we
    -2.33
     lament
    -2.33
    谖
    -2.31
    д
    -2.31
    龵
    -2.27
    嵙
    -2.25
    鍇
    -2.19
     ´
    -2.17
    锨
    -2.17
    POSITIVE LOGITS
    谙
    2.22
     Menurut
    2.22
    <bos>
    2.20
    .
    2.19
    人也
    2.09
    6
    2.06
     Terkait
    2.05
    that
    2.03
    龊
    2.02
    Semoga
    1.94
    Activations Density 0.002%

    No Known Activations