© 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. 40-GEMMASCOPE-2-RES-262K
    7. 220025
    Prev
    Next
    INDEX
    Explanations

    Directed Graphs

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     실
    0.41
     ence
    0.39
    ABLES
    0.37
     sce
    0.36
     seg
    0.35
    ologous
    0.35
    ggle
    0.35
    ゆ
    0.35
     internationaux
    0.34
     بشر
    0.34
    POSITIVE LOGITS
    ἆ
    0.49
    పాల
    0.44
     Tuning
    0.43
     Dimensions
    0.42
     Wetland
    0.42
     Dimension
    0.42
     dimensi
    0.42
    絃
    0.41
     издели
    0.41
    कहीं
    0.41
    Activations Density 0.006%

    No Known Activations