© 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. 127288
    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
     There
    -2.20
     Also
    -1.82
     When
    -1.80
     Using
    -1.77
     Does
    -1.77
     Only
    -1.68
    —
    -1.67
    x
    -1.66
    ים
    -1.65
     ONLY
    -1.57
    POSITIVE LOGITS
     of
    2.77
     afbeeldingen
    2.14
    耵
    2.06
     muziek
    1.91
     aandacht
    1.90
     wijn
    1.88
    哏
    1.85
    ではまた
    1.84
    睏
    1.84
     tegens
    1.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.