© 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. 41-GEMMASCOPE-2-RES-262K
    7. 103609
    Prev
    Next
    INDEX
    Explanations

    quantities, occurrences, or contracts

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    EF
    0.46
    EH
    0.43
    Ac
    0.42
    Ef
    0.39
     রজ
    0.39
    тна
    0.38
    ARMA
    0.38
     bio
    0.38
    Ma
    0.38
    누
    0.38
    POSITIVE LOGITS
    ://${
    0.41
     prens
    0.40
    ިޔ
    0.39
     স্বায়ত্ত
    0.39
     ionizing
    0.38
     Tear
    0.37
     اش
    0.37
    िये
    0.37
     Myerson
    0.37
     auk
    0.36
    Activations Density 0.054%

    No Known Activations