© 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. 58166
    Prev
    Next
    INDEX
    Explanations

    golf swing

    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
    INH
    -0.84
     GOB
    -0.82
    GRAM
    -0.81
    NOV
    -0.81
    FIM
    -0.80
    Ṅ
    -0.79
     Felic
    -0.79
    Noc
    -0.76
    NBA
    -0.76
     Noc
    -0.75
    POSITIVE LOGITS
     swing
    1.70
     swings
    1.41
    Swing
    1.29
    swing
    1.28
     Swing
    1.27
     swinging
    1.21
     swung
    1.14
     takeaway
    0.99
     Schülern
    0.84
     square
    0.83
    Activations Density 0.008%

    No Known Activations