© 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. 42402
    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
     Selv
    -1.02
     alrededores
    -0.98
     aktivieren
    -0.96
     signalled
    -0.96
    後の
    -0.94
    Related
    -0.90
    êtement
    -0.90
    あれ
    -0.89
    biť
    -0.88
     mythological
    -0.87
    POSITIVE LOGITS
    umers
    1.07
     grateful
    1.07
    ضات
    1.04
     necesariamente
    1.02
    Děkuji
    0.97
    PLAINT
    0.95
    ofing
    0.94
    PARATOR
    0.94
    cings
    0.94
     dismin
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.