© 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. 93162
    Prev
    Next
    INDEX
    Explanations

    soul and funk music

    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
     Halsey
    -0.93
     tattoo
    -0.84
    coring
    -0.82
     aviones
    -0.80
    americana
    -0.80
     alivio
    -0.80
    caling
    -0.79
    タレ
    -0.78
     pixel
    -0.77
     acoustic
    -0.76
    POSITIVE LOGITS
     Funk
    1.40
     funk
    1.29
     Soul
    1.27
    funk
    1.23
    Funk
    1.23
    Soul
    1.23
     soul
    1.18
     SOUL
    1.01
     Funky
    1.00
    funky
    0.97
    Activations Density 0.034%

    No Known Activations