© 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. 38618
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    緜
    -2.00
    Most
    -1.61
     Commentaires
    -1.59
     compleanno
    -1.59
     incomplète
    -1.58
     Ansprüche
    -1.57
    媄
    -1.57
    </u>
    -1.54
     artikelen
    -1.52
     休閒
    -1.52
    POSITIVE LOGITS
    明显的
    1.69
     are
    1.69
    你在
    1.61
     voor
    1.59
     wer
    1.58
    ’，
    1.54
    晚安
    1.48
    ’
    1.45
    矗
    1.45
    VK
    1.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.