© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60665
    Prev
    Next
    INDEX
    Explanations

    hand / hold / grip

    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
     TECHNOLOGIES
    -0.81
     akti
    -0.81
     saks
    -0.80
     Cosmetics
    -0.78
    academic
    -0.77
     sats
    -0.75
    contenedor
    -0.75
     Piotr
    -0.75
     akade
    -0.75
     одежды
    -0.74
    POSITIVE LOGITS
     Touch
    0.93
     Gefühl
    0.83
    QMetaType
    0.77
    bric
    0.77
     Дже
    0.76
     更
    0.75
    CppMethod
    0.73
    ถือ
    0.73
    臂
    0.72
     rifle
    0.70
    Activations Density 0.010%

    No Known Activations