© 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. 24903
    Prev
    Next
    INDEX
    Explanations

    functional programming, map, collect, reduce

    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
     foreach
    0.54
    foreach
    0.45
    forEach
    0.44
     getDescription
    0.42
    ForEach
    0.38
    赅
    0.37
     IEnumerable
    0.37
     Velocity
    0.37
    contains
    0.37
    丳
    0.37
    POSITIVE LOGITS
    Scan
    0.45
     scan
    0.45
    scan
    0.45
    éreo
    0.42
     Scan
    0.42
     meu
    0.41
     מג
    0.41
     auditing
    0.40
     तोला
    0.40
    ste
    0.39
    Activations Density 0.002%

    No Known Activations