© 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. 113820
    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
    斯的
    -1.01
     elb
    -0.95
    槻
    -0.93
     genial
    -0.91
    ровке
    -0.88
    過ぎる
    -0.88
     eloquent
    -0.87
    ПРО
    -0.87
    ovu
    -0.87
    нове
    -0.85
    POSITIVE LOGITS
     aconteceu
    0.99
     acontece
    0.96
     time
    0.96
     vormen
    0.96
     ocorre
    0.94
     diretto
    0.93
    ָא
    0.92
     migliorare
    0.91
     gezond
    0.91
     eenige
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.