© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77760
    Prev
    Next
    INDEX
    Explanations

    measuring execution time

    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
     историю
    -0.81
    фера
    -0.78
    áles
    -0.77
     hü
    -0.71
    ˀ
    -0.71
     presso
    -0.70
    ição
    -0.70
    idor
    -0.70
     menggelar
    -0.68
     mengumumkan
    -0.68
    POSITIVE LOGITS
     elapsed
    2.36
     time
    2.16
     spent
    2.06
     duration
    1.95
    elapsed
    1.77
     spend
    1.75
     execution
    1.74
     затра
    1.66
    耗
    1.65
     spending
    1.60
    Activations Density 0.017%

    No Known Activations