© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91992
    Prev
    Next
    INDEX
    Explanations

    rush hour and prime 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
     pasal
    -0.81
     balon
    -0.79
    ベツ
    -0.79
    COLE
    -0.78
    stoffen
    -0.78
     violenza
    -0.78
     faa
    -0.77
     Pâ
    -0.77
    Elastic
    -0.76
     jährlich
    -0.76
    POSITIVE LOGITS
     rush
    3.59
     peak
    2.78
    rush
    2.56
     Rush
    2.47
    Rush
    2.38
    peak
    1.95
     Peak
    1.90
    Peak
    1.88
     RUSH
    1.88
     rushes
    1.84
    Activations Density 0.024%

    No Known Activations