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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 243
    Prev
    Next
    INDEX
    Explanations

    CPU speeds and frequencies

    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
     βα
    -0.79
    redor
    -0.71
    Shy
    -0.69
     zeich
    -0.68
     dólares
    -0.68
    cepted
    -0.67
     プ
    -0.66
    dataSet
    -0.66
    *************/
    -0.66
    зовать
    -0.66
    POSITIVE LOGITS
    GHz
    1.20
     GHz
    1.19
     Turbo
    0.91
     turbo
    0.88
    Turbo
    0.87
     frequencies
    0.85
     speeds
    0.83
    turbo
    0.82
     subprocess
    0.82
    Clock
    0.80
    Activations Density 0.028%

    No Known Activations