© 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. 86240
    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
     sooooo
    -1.09
     gì
    -1.05
     enhances
    -0.98
     continual
    -0.97
     nestled
    -0.96
     any
    -0.96
     sparked
    -0.94
    百姓
    -0.94
     kệ
    -0.94
    Они
    -0.93
    POSITIVE LOGITS
    unfortunately
    1.12
    ayet
    1.05
     distinctive
    1.02
     schlaf
    1.02
    nce
    1.01
    particularly
    0.98
    鸸
    0.96
     delightfully
    0.96
    approximately
    0.95
     tausend
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.