© 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. 71993
    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
    Whew
    -0.97
    perl
    -0.95
    SWIG
    -0.89
    მ
    -0.89
     Expiration
    -0.88
    AFFIRMED
    -0.86
    还有一个
    -0.85
    Phew
    -0.85
     {
    -0.84
    emis
    -0.84
    POSITIVE LOGITS
     solches
    1.11
    ності
    1.02
    Ḡ
    0.92
    訪問
    0.91
    iteracy
    0.89
     حمله
    0.89
    釦
    0.88
    週末
    0.87
    джет
    0.84
    qrt
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.