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. 8045
    Prev
    Next
    INDEX
    Explanations

    temperature units: C, F

    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
    фере
    -0.81
    going
    -0.79
    BASELINE
    -0.77
    GroupLayout
    -0.75
    ddots
    -0.75
    umab
    -0.74
    g
    -0.74
    sizeof
    -0.74
    ifer
    -0.73
    プレー
    -0.73
    POSITIVE LOGITS
     Celsius
    1.66
     celsius
    1.34
     Fahrenheit
    1.33
    Fahren
    1.05
     centi
    1.05
     Congresso
    0.93
    Celsius
    0.92
     belangrijk
    0.82
     Brix
    0.82
     Kelvin
    0.82
    Activations Density 0.013%

    No Known Activations