© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127529
    Prev
    Next
    INDEX
    Explanations

    closing quote or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’，
    -1.99
    鸰
    -1.84
     також
    -1.80
     και
    -1.73
     also
    -1.68
     și
    -1.67
    —”
    -1.59
    .’
    -1.59
    咙
    -1.59
    縝
    -1.58
    POSITIVE LOGITS
    ."
    2.56
     '
    2.52
     -
    2.30
     "
    2.30
    ,"
    2.17
     -'
    1.87
    '
    1.84
     '.
    1.74
    鸲
    1.73
     -"
    1.70
    Activations Density 0.090%

    No Known Activations