© 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. 103516
    Prev
    Next
    INDEX
    Explanations

    pro-EU and regions

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

    language generation, classification

    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
     biomed
    0.50
     вод
    0.47
     ziek
    0.46
     Supp
    0.46
    i
    0.46
    ină
    0.46
     Privat
    0.45
     곡
    0.44
    halb
    0.44
     Regular
    0.43
    POSITIVE LOGITS
    ECTOR
    0.51
    USION
    0.48
    REGION
    0.48
    UNION
    0.47
    FLOW
    0.44
    겔
    0.44
    でも
    0.43
    Ontario
    0.43
     unión
    0.43
    GINIA
    0.43
    Activations Density 0.000%

    No Known Activations