© 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. 226681
    Prev
    Next
    INDEX
    Explanations

    discuss, brain, Italian, Red

    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
    et
    0.62
    ée
    0.59
    ا
    0.57
    ar
    0.54
    A
    0.53
    em
    0.53
    âmica
    0.52
    on
    0.52
    end
    0.51
    á
    0.51
    POSITIVE LOGITS
     winnings
    0.50
     sparkles
    0.46
     whence
    0.46
     grants
    0.44
    წი
    0.43
     bouncy
    0.43
     pencils
    0.43
     alkan
    0.43
    ("***
    0.42
    မူ
    0.42
    Activations Density 0.000%

    No Known Activations