© 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. 63570
    Prev
    Next
    INDEX
    Explanations

    early nineties

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

    parts of speech (verbs, nouns)

    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
     Джон
    0.45
     deficient
    0.45
     defList
    0.44
     voet
    0.44
    Ꮈ
    0.44
     a
    0.43
     Corresponding
    0.43
     emig
    0.43
     diarrh
    0.43
     metallurgical
    0.42
    POSITIVE LOGITS
    มา
    0.51
    ise
    0.48
    รูปแบบ
    0.48
    ก
    0.48
    ves
    0.47
    agian
    0.47
    bare
    0.47
    เบ
    0.47
    themes
    0.46
    jasama
    0.46
    Activations Density 0.000%

    No Known Activations