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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110791
    Prev
    Next
    INDEX
    Explanations

    smooth R&B soul 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
     Rentals
    -0.87
     Textiles
    -0.85
     qr
    -0.82
     garaje
    -0.82
     Metallica
    -0.82
     kath
    -0.81
    enzen
    -0.78
     ★★★★
    -0.77
     Loki
    -0.77
    隹
    -0.77
    POSITIVE LOGITS
     smooth
    1.46
    Smooth
    1.41
    smooth
    1.41
     Smooth
    1.39
     soul
    1.39
     Soul
    1.38
     smoothness
    1.20
    Soul
    1.13
     soulful
    1.09
     R
    1.04
    Activations Density 0.060%

    No Known Activations