© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130291
    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
    姈
    -1.56
    𓋼
    -1.54
     alerg
    -1.53
    睨
    -1.52
     tuto
    -1.52
    珦
    -1.52
     hôtel
    -1.51
     mulus
    -1.51
     في
    -1.46
     ۱۳
    -1.45
    POSITIVE LOGITS
    t
    1.91
     hlavy
    1.91
     którzy
    1.83
    ťaž
    1.77
    wasn
    1.67
     なり
    1.63
     детей
    1.63
    腦
    1.60
    </h2>
    1.55
     jesteśmy
    1.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.