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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8390
    Prev
    Next
    INDEX
    Explanations

    geothermal drilling systems

    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
     during
    -0.74
    ماني
    -0.71
    Цитата
    -0.71
     виді
    -0.70
    butter
    -0.69
    вз
    -0.68
     fotografico
    -0.68
    †
    -0.68
     alight
    -0.68
     fully
    -0.68
    POSITIVE LOGITS
     geothermal
    1.27
     thermal
    1.20
     Thermal
    1.18
    Thermal
    1.05
    thermal
    0.96
     underground
    0.91
     Underground
    0.87
     GSH
    0.87
     Geothermal
    0.84
     borehole
    0.83
    Activations Density 0.008%

    No Known Activations