© 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. 82623
    Prev
    Next
    INDEX
    Explanations

    child playing

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

    domain name, cat-cow stretch

    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
     профилакти
    0.50
    ский
    0.50
     бизнеса
    0.47
    asă
    0.47
     юриди
    0.47
     diminue
    0.46
    p
    0.46
     법
    0.46
     губер
    0.45
    didn
    0.45
    POSITIVE LOGITS
     Beweg
    0.56
     Drawing
    0.50
     Angles
    0.49
     Boundaries
    0.48
     Interaction
    0.47
     Drawings
    0.47
     Ruf
    0.46
     Each
    0.46
     Between
    0.45
     Characters
    0.45
    Activations Density 0.001%

    No Known Activations