© 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. 130059
    Prev
    Next
    INDEX
    Explanations

    table in code

    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
     All
    0.42
     Databases
    0.39
     Lä
    0.38
    மாக
    0.37
     Bin
    0.37
     MATRIX
    0.37
    மாகும்
    0.36
     நா
    0.36
    出品
    0.36
     ਸ
    0.35
    POSITIVE LOGITS
     locked
    0.39
    бой
    0.39
    jre
    0.38
    free
    0.37
    দে
    0.37
     হঠাৎ
    0.37
     জোট
    0.37
     შორის
    0.37
     desperate
    0.36
    jars
    0.36
    Activations Density 0.000%

    No Known Activations