© 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. 91214
    Prev
    Next
    INDEX
    Explanations

    bowled cricket

    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
     Dun
    -0.77
     gyors
    -0.76
    ठी
    -0.72
     Rass
    -0.71
    erialize
    -0.71
    ardom
    -0.70
     giocatori
    -0.69
    stino
    -0.68
    我还是
    -0.68
     rendono
    -0.68
    POSITIVE LOGITS
     figures
    1.21
     bowling
    1.02
     spell
    0.95
    figures
    0.94
     bowls
    0.90
    Figures
    0.85
     FIGURES
    0.84
     bowl
    0.81
     unchanged
    0.81
    fgets
    0.80
    Activations Density 0.013%

    No Known Activations