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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 697
    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
     TextView
    -0.91
    頸
    -0.89
    dogs
    -0.89
    Dogs
    -0.89
    getCategory
    -0.88
    庵
    -0.87
    بيه
    -0.87
     spawn
    -0.86
     Nicholas
    -0.85
     силы
    -0.82
    POSITIVE LOGITS
     selben
    1.15
     wielu
    1.09
     消防
    1.05
     Même
    0.99
     respiración
    0.98
     Dacă
    0.96
     complètement
    0.96
    idalgo
    0.95
     toreb
    0.95
     económicas
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.