© 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. 10-GEMMASCOPE-RES-131K
    7. 12047
    Prev
    Next
    INDEX
    Explanations

    dance and ballet performances

    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_10/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
     you
    -1.69
    d
    -1.62
    p
    -1.48
    R
    -1.41
    ing
    -1.41
    x
    -1.41
    c
    -1.34
     values
    -1.34
    w
    -1.34
    ap
    -1.31
    POSITIVE LOGITS
    💃
    1.70
     黑色
    1.60
     choreographer
    1.44
    Polska
    1.42
     perna
    1.38
     atle
    1.31
     opini
    1.31
     choreography
    1.30
    dancing
    1.30
    ！”
    1.28
    Activations Density 0.042%

    No Known Activations