© 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. 216199
    Prev
    Next
    INDEX
    Explanations

    professional entities classifying roles

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

    upstream and downstream

    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
    oru
    0.50
    Ї
    0.49
    an
    0.48
    ada
    0.46
     резер
    0.46
    READER
    0.44
    OR
    0.44
    AN
    0.44
    AIC
    0.44
    ad
    0.43
    POSITIVE LOGITS
     fréquemment
    0.47
    目光
    0.46
     webs
    0.44
     hins
    0.44
     huk
    0.43
    服务
    0.43
    缠
    0.42
    veillance
    0.42
     économiques
    0.42
     suç
    0.42
    Activations Density 0.001%

    No Known Activations