© 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. 57388
    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
     afbeeldingen
    -1.02
     Indon
    -0.99
     ''.
    -0.98
     forestal
    -0.95
    らなかった
    -0.94
     Inspections
    -0.94
    ἳ
    -0.93
    ទ
    -0.91
     prácticamente
    -0.90
     жесто
    -0.90
    POSITIVE LOGITS
    ModelAndView
    0.95
    deauna
    0.94
     confirmé
    0.92
     encanta
    0.91
     выбран
    0.91
    gies
    0.91
     opérés
    0.90
     cuisson
    0.89
     divertidas
    0.85
     Functional
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.