© 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. 211983
    Prev
    Next
    INDEX
    Explanations

    foreign and sheep

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

    delivery of services or goods

    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
     o
    0.47
     newValue
    0.44
     εκ
    0.42
     needle
    0.42
     clean
    0.41
     eel
    0.41
     new
    0.41
     ለአ
    0.41
     HY
    0.40
     liht
    0.40
    POSITIVE LOGITS
    шибка
    0.50
    ಸ್ತು
    0.50
    胤
    0.49
    زاء
    0.46
    人的
    0.45
    国家的
    0.44
    澧
    0.44
    心中
    0.44
    Conte
    0.44
    olutamente
    0.44
    Activations Density 0.001%

    No Known Activations