© 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. 77844
    Prev
    Next
    INDEX
    Explanations

    phrases with specific words

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

    multi-language occurrences and quantities

    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
    琢
    0.47
    ﺗ
    0.45
    FY
    0.44
    任
    0.43
    👥
    0.43
    🏦
    0.41
    }/
    0.39
    kä
    0.39
    得意
    0.39
    进展
    0.38
    POSITIVE LOGITS
     marinas
    0.52
     многи
    0.51
     myriad
    0.49
     বছর
    0.49
     autres
    0.49
    وني
    0.48
     kilomètres
    0.47
     другими
    0.46
     bezieht
    0.45
     innymi
    0.45
    Activations Density 0.001%

    No Known Activations