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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8518
    Prev
    Next
    INDEX
    Explanations

    electrical heating 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
     Rites
    -0.70
    Lik
    -0.69
    ACIONES
    -0.68
     melissa
    -0.68
     valeurs
    -0.67
    igation
    -0.66
    öny
    -0.66
    RetentionPolicy
    -0.65
    瑛
    -0.65
    oye
    -0.65
    POSITIVE LOGITS
     heating
    2.64
     Heating
    1.95
     heater
    1.88
     element
    1.81
     heaters
    1.80
    Heating
    1.80
    heating
    1.76
     elements
    1.52
     Element
    1.46
     nich
    1.43
    Activations Density 0.060%

    No Known Activations