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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100254
    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
     melang
    -1.10
     EVENTS
    -1.09
    当然
    -1.05
     littéraire
    -1.02
     кнопку
    -1.00
     menghubungi
    -1.00
     maksimal
    -0.95
     otomatis
    -0.94
     vilka
    -0.94
     kapsul
    -0.93
    POSITIVE LOGITS
    ’
    1.25
     this
    1.03
     plans
    0.94
    恳
    0.93
     hope
    0.91
    </i>
    0.90
    脖
    0.86
     tämän
    0.86
    嘻
    0.85
    いけ
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.