© 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. 83072
    Prev
    Next
    INDEX
    Explanations

    swing or whip

    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
    SAY
    -0.77
    éz
    -0.75
    ługo
    -0.75
     Vittorio
    -0.74
    撐
    -0.72
    nto
    -0.72
    okia
    -0.70
    ⏏
    -0.70
    yat
    -0.70
    を着
    -0.69
    POSITIVE LOGITS
     swinging
    2.95
     swing
    2.73
     swung
    2.63
    swing
    2.58
     Swing
    2.55
    Swing
    2.47
     swings
    2.42
     whip
    2.05
     whipping
    1.95
     whips
    1.76
    Activations Density 0.049%

    No Known Activations