© 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. 107494
    Prev
    Next
    INDEX
    Explanations

    swim and swimming

    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
    FieldError
    -0.81
    peteer
    -0.80
     Bedding
    -0.80
    avoie
    -0.79
    طن
    -0.78
     harap
    -0.78
     Lacrosse
    -0.77
     RuntimeError
    -0.76
    дэ
    -0.74
     الظ
    -0.73
    POSITIVE LOGITS
     swim
    2.31
     swimming
    2.25
     Swim
    1.86
     drowning
    1.80
    Swimming
    1.77
    Swim
    1.73
     Swimming
    1.70
    swimming
    1.69
    swim
    1.61
     swims
    1.59
    Activations Density 0.009%

    No Known Activations