© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63381
    Prev
    Next
    INDEX
    Explanations

    core of, limit to, Infant bassinet

    np_acts-logits-general · gemini-2.5-flash-lite

    lists of X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     মূল্যা
    0.51
     eu
    0.50
     পরবর্তী
    0.47
     понравилось
    0.46
     साल
    0.46
    分区
    0.46
     появилась
    0.45
     שנה
    0.45
    赡
    0.45
     layanan
    0.44
    POSITIVE LOGITS
     kojim
    0.47
    íny
    0.45
     regimens
    0.45
    тини
    0.44
    rocities
    0.43
    юро
    0.43
    inyl
    0.43
     editorials
    0.42
    itius
    0.42
    跎
    0.41
    Activations Density 0.000%

    No Known Activations