© 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. 85983
    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
     Instead
    -0.92
     lâng
    -0.90
    雖然
    -0.88
     刷
    -0.87
    selbe
    -0.86
     We
    -0.86
     Muerte
    -0.85
    ńskie
    -0.85
     Exactly
    -0.84
     vorrei
    -0.83
    POSITIVE LOGITS
    Ｍ
    1.28
     now
    1.09
    NECTIONS
    1.09
     nadat
    1.00
    琶
    0.99
     pessoais
    0.98
    ViewChild
    0.96
    UNDEFINED
    0.96
     Ria
    0.94
     television
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.