© 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. 189648
    Prev
    Next
    INDEX
    Explanations

    Bowling League

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

    everyone called

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ᑉ
    0.55
    BOUND
    0.53
    𝘖
    0.53
    ケイ
    0.53
    ㅅ
    0.53
    𝑅
    0.52
    欄
    0.51
    ी
    0.50
     ふ
    0.50
    उदा
    0.50
    POSITIVE LOGITS
     artic
    0.50
     in
    0.47
     desconoc
    0.47
     Family
    0.44
     Dee
    0.43
     horizont
    0.43
     rédu
    0.43
     amplification
    0.43
     Jac
    0.42
     recort
    0.42
    Activations Density 0.001%

    No Known Activations