© 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. 3196
    Prev
    Next
    INDEX
    Explanations

    basketball performance and scoring

    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
    esthesia
    -0.84
     viajar
    -0.72
     Judo
    -0.71
    っぱり
    -0.71
     menjalankan
    -0.70
    nol
    -0.68
    elems
    -0.68
     soldati
    -0.68
     defensive
    -0.67
     flä
    -0.67
    POSITIVE LOGITS
     scoring
    3.00
     Scoring
    2.53
    Scoring
    2.47
     scored
    2.41
    scoring
    2.36
     scorer
    2.08
     score
    2.06
     scorers
    1.88
     Score
    1.75
    scored
    1.72
    Activations Density 0.017%

    No Known Activations