© 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. 235679
    Prev
    Next
    INDEX
    Explanations

    organized materials

    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
    ệt
    0.53
    ạy
    0.42
     rep
    0.41
    ings
    0.39
    합
    0.39
    Cameras
    0.38
    ędzie
    0.38
    ନ୍ଦ
    0.38
     randomized
    0.37
     cucumbers
    0.37
    POSITIVE LOGITS
     있는
    0.57
    ستان
    0.55
     ชอบ
    0.52
     자리
    0.49
     เอา
    0.49
     favorito
    0.49
     位置
    0.49
    cendo
    0.47
    |+
    0.47
     있어요
    0.46
    Activations Density 0.000%

    No Known Activations