© 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. 76834
    Prev
    Next
    INDEX
    Explanations

    beats per measure

    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
    ➙
    -0.81
    ENODEV
    -0.76
    ssos
    -0.74
     webinars
    -0.73
    ission
    -0.73
    ודש
    -0.73
    athon
    -0.73
    Tikang
    -0.72
    дьми
    -0.71
    iramente
    -0.71
    POSITIVE LOGITS
     measures
    2.89
     measure
    2.75
    measure
    2.50
     Measures
    2.42
    Measures
    2.38
     Measure
    2.31
    measures
    2.31
    Measure
    2.28
     MEASURES
    2.13
     medidas
    1.92
    Activations Density 0.018%

    No Known Activations