© 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. 109634
    Prev
    Next
    INDEX
    Explanations

    baseball pitches and zones

    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
    zünd
    -0.89
    向前
    -0.85
    греди
    -0.84
    utiva
    -0.80
     Albums
    -0.80
    Entrée
    -0.79
    Tous
    -0.79
    λλα
    -0.77
     possessions
    -0.76
    сову
    -0.76
    POSITIVE LOGITS
     outside
    1.09
     zone
    1.03
     zones
    0.98
     letter
    0.97
     Zone
    0.97
     Outside
    0.96
     pitches
    0.89
     Zones
    0.89
     location
    0.88
     EZ
    0.86
    Activations Density 0.011%

    No Known Activations