© 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. 1798
    Prev
    Next
    INDEX
    Explanations

    pace and tempo descriptions

    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
    Faj
    -0.76
     okolí
    -0.74
    Mazda
    -0.72
    Italien
    -0.71
    酎
    -0.71
    🪀
    -0.70
    聆
    -0.70
    Cancelar
    -0.69
    ogno
    -0.68
    šenie
    -0.68
    POSITIVE LOGITS
     pace
    6.25
     Pace
    4.03
    Pace
    3.94
     paced
    3.77
     tempo
    3.75
    pace
    3.52
     pacing
    3.36
    paced
    3.14
     ritmo
    3.13
     paces
    2.95
    Activations Density 0.036%

    No Known Activations