© 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. 92934
    Prev
    Next
    INDEX
    Explanations

    opening batsman

    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
     sweeps
    -0.77
    Achter
    -0.74
    的后
    -0.71
    ้อง
    -0.71
     μα
    -0.68
     middle
    -0.68
    wors
    -0.67
     Holanda
    -0.66
    Kö
    -0.65
     midfield
    -0.65
    POSITIVE LOGITS
     openers
    1.88
     opening
    1.84
    opening
    1.58
     opener
    1.39
    Opening
    1.36
     Opening
    1.30
     openings
    1.23
     apertura
    1.21
     OPENING
    1.20
    apertura
    1.17
    Activations Density 0.010%

    No Known Activations