© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108046
    Prev
    Next
    INDEX
    Explanations

    baseball pitching

    np_acts-logits-general · gemini-2.5-flash-lite

    baseball pitching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     खरीदारी
    0.56
    店铺
    0.51
     меню
    0.48
    菜单
    0.46
    🥪
    0.46
    জ্জনক
    0.45
     দোকানে
    0.44
    買い物
    0.44
    🏬
    0.44
    ্যাড
    0.43
    POSITIVE LOGITS
     pitching
    0.71
     pitchers
    0.63
     pitcher
    0.60
     pitched
    0.58
     pitches
    0.53
    pitched
    0.52
     pitch
    0.51
     irrig
    0.50
     Pitch
    0.47
    贷
    0.46
    Activations Density 0.081%

    No Known Activations