© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43313
    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
     variaciones
    -1.07
     seven
    -1.03
     variadas
    -0.98
     conocen
    -0.96
     six
    -0.94
     dziecię
    -0.94
     Such
    -0.93
     białe
    -0.92
     中華
    -0.92
     three
    -0.91
    POSITIVE LOGITS
     réfugiés
    1.05
     susten
    1.01
     Rhyth
    0.98
     analys
    0.96
     هناك
    0.94
    äter
    0.94
     publicités
    0.93
     négociations
    0.93
    䊉
    0.92
     répé
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.