© 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-16K
    7. 6594
    Prev
    Next
    INDEX
    Explanations

    * with titles

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     thậm
    0.37
     လက်
    0.36
    鸠
    0.36
     petits
    0.35
    inture
    0.35
    VARCHAR
    0.35
    هاء
    0.35
    ềm
    0.34
     المع
    0.34
     برا
    0.34
    POSITIVE LOGITS
     비롯
    0.49
    、
    0.47
    ;
    0.46
    ，
    0.42
     všetky
    0.42
    +...+
    0.41
     replicates
    0.41
    updater
    0.40
    依次
    0.40
    crib
    0.39
    Activations Density 0.510%

    No Known Activations