© 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. 32871
    Prev
    Next
    INDEX
    Explanations

    statistics and football actions

    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
    FormBorderStyle
    -0.83
    WON
    -0.77
    angue
    -0.76
     Jacuzzi
    -0.73
     lég
    -0.73
    家が
    -0.72
    ienė
    -0.72
    сол
    -0.72
    FIS
    -0.72
     Debra
    -0.72
    POSITIVE LOGITS
     defended
    1.23
     breakup
    1.22
     defends
    1.15
     fumble
    1.11
    break
    1.08
     forced
    1.05
     passes
    1.02
     break
    1.02
     Forced
    1.00
     deflection
    0.94
    Activations Density 0.009%

    No Known Activations