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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109850
    Prev
    Next
    INDEX
    Explanations

    reserved keyword/context

    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
    ărilor
    -0.92
    mone
    -0.88
    ssan
    -0.78
     Seidel
    -0.75
    dataIndex
    -0.73
    клар
    -0.72
     Latex
    -0.71
    Ự
    -0.71
    ciaio
    -0.69
     SOAP
    -0.68
    POSITIVE LOGITS
     reserved
    0.88
    reserved
    0.87
     réservés
    0.85
     réservé
    0.80
    tingen
    0.79
    Reserved
    0.78
    erende
    0.77
    artig
    0.76
     thickness
    0.75
    ору
    0.75
    Activations Density 0.023%

    No Known Activations