© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48466
    Prev
    Next
    INDEX
    Explanations

    feature codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sera
    0.43
     tulee
    0.41
     △
    0.41
     sorgen
    0.40
     vie
    0.39
     entwickeln
    0.39
     komma
    0.39
     lehetős
    0.39
     coexist
    0.39
     produ
    0.39
    POSITIVE LOGITS
    Б
    0.52
    gian
    0.51
    옥
    0.47
    после
    0.46
     ಉತ್
    0.46
    before
    0.46
    grandfather
    0.45
    鱿
    0.45
    レー
    0.45
    ड
    0.45
    Activations Density 0.004%

    No Known Activations