© 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. 83889
    Prev
    Next
    INDEX
    Explanations

    progress

    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
    Negative Logits
    搆
    -2.09
     foon
    -2.08
    </h1>
    -2.08
    capacete
    -2.06
     fevere
    -2.05
    隳
    -2.02
     twa
    -1.98
     juf
    -1.96
    ꜆
    -1.95
     fint
    -1.91
    POSITIVE LOGITS
    ’
    2.77
    ↵
    2.48
     ainsi
    2.23
    The
    2.09
     '
    2.06
     ,
    1.98
     \\
    1.89
    这
    1.86
     We
    1.86
    という感じ
    1.84
    Activations Density 0.016%

    No Known Activations