© 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. 91050
    Prev
    Next
    INDEX
    Explanations

    local community

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

    abdominal aortic aneurysm

    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
    otions
    0.50
    idencia
    0.49
    imd
    0.49
    ibles
    0.48
    ibs
    0.47
    Options
    0.46
    lear
    0.46
    ѣ
    0.46
    igations
    0.45
     anteriores
    0.45
    POSITIVE LOGITS
     nisam
    0.57
     mağ
    0.43
     isometry
    0.43
     zespół
    0.43
    祕
    0.42
     মাধ্যমে
    0.42
    લમાં
    0.42
    ził
    0.42
     sœur
    0.42
     alpin
    0.41
    Activations Density 0.000%

    No Known Activations