Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110364
    Prev
    Next
    INDEX
    Explanations

    HTML form and layout elements

    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
    Propiedades
    -0.88
    eraard
    -0.88
    Análisis
    -0.88
     facilement
    -0.85
    spooky
    -0.83
    CardHeader
    -0.83
    Thema
    -0.83
    Función
    -0.82
     specta
    -0.80
     specif
    -0.80
    POSITIVE LOGITS
    table
    1.05
     there
    1.03
     here
    1.01
     table
    0.99
     form
    0.96
     rows
    0.96
     row
    0.94
    Row
    0.91
     Table
    0.91
    Table
    0.90
    Activations Density 0.011%

    No Known Activations