© 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. 153016
    Prev
    Next
    INDEX
    Explanations

    Nineveh and biblical characters

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

    sometimes, carriers, invoices, groups

    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
    '
    0.61
     faci
    0.48
     elixir
    0.44
     মুহূর্ত
    0.43
     guan
    0.42
     ejer
    0.42
    明け
    0.41
     orta
    0.41
     LUCKY
    0.40
     विच
    0.40
    POSITIVE LOGITS
    leValue
    0.47
    垢
    0.46
    ంద్ర
    0.46
    ър
    0.45
    ണ്ഡി
    0.45
    等人
    0.43
    StubCompat
    0.43
    ObjData
    0.42
    峋
    0.42
    og
    0.41
    Activations Density 0.001%

    No Known Activations