© 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. 98699
    Prev
    Next
    INDEX
    Explanations

    technical terms and 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
    Negative Logits
     Quais
    -2.02
    ずつ
    -1.96
    pendente
    -1.95
     ͡°
    -1.93
     AQUI
    -1.86
    ⁛
    -1.86
    нятно
    -1.85
    が見えて
    -1.83
     ücretsiz
    -1.82
    alamualaikum
    -1.82
    POSITIVE LOGITS
    et
    2.50
    .”
    2.48
    </h3>
    2.36
    ,“
    2.30
    "));
    2.30
     \\
    2.28
    ed
    2.23
    O
    2.17
    ﮏ
    2.13
    </h5>
    2.08
    Activations Density 1.115%

    No Known Activations