© 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. 102849
    Prev
    Next
    INDEX
    Explanations

    pipe dream, expenditures between

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

    cortical reorganization

    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
    ים
    0.50
    钢琴
    0.49
     cartão
    0.46
    矵
    0.46
     helmet
    0.46
     เฮ
    0.46
     كلمة
    0.45
     powied
    0.45
     చెప్పు
    0.44
     配置
    0.44
    POSITIVE LOGITS
     K
    0.52
     SOI
    0.50
    fei
    0.49
     P
    0.48
     A
    0.47
     К
    0.46
    FindBy
    0.45
    akuza
    0.45
     Yang
    0.44
    ua
    0.44
    Activations Density 0.000%

    No Known Activations