© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 192352
    Prev
    Next
    INDEX
    Explanations

    baseball actions and equipment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sho
    0.39
     DVD
    0.38
    urals
    0.38
    cd
    0.38
    Synopsis
    0.37
    す楽
    0.36
    essing
    0.36
    ;//
    0.35
     REACH
    0.35
    DVD
    0.35
    POSITIVE LOGITS
     batting
    0.57
     Batter
    0.54
     batters
    0.52
     batter
    0.49
     pitcher
    0.48
     Pitch
    0.45
     pitchers
    0.45
     bate
    0.43
     BAT
    0.41
     Bat
    0.41
    Activations Density 0.005%

    No Known Activations