© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106191
    Prev
    Next
    INDEX
    Explanations

    baseball pitching

    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
    Negative Logits
     players
    -0.91
    plays
    -0.86
     diarios
    -0.82
    Plays
    -0.81
     Plays
    -0.80
     plays
    -0.80
     Players
    -0.79
     play
    -0.79
    players
    -0.79
    outil
    -0.76
    POSITIVE LOGITS
     pitching
    2.00
     pitch
    1.73
    Pitch
    1.70
     pitches
    1.59
    pitch
    1.53
     pitched
    1.52
     Pitch
    1.45
     mound
    1.32
     pitcher
    1.27
     Pitcher
    1.23
    Activations Density 0.042%

    No Known Activations