© 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. 12154
    Prev
    Next
    INDEX
    Explanations

    Tucson and Arizona locations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    0
    -2.56
    7
    -2.33
    8
    -2.28
    3
    -2.23
    9
    -2.22
    4
    -2.19
    </sup>
    -2.17
    1
    -2.16
    2
    -2.06
     coreano
    -1.94
    POSITIVE LOGITS
    謌
    2.05
     be
    1.84
    СЫ
    1.80
     manteniendo
    1.78
     mantener
    1.66
     numerosos
    1.62
    辂
    1.58
     drž
    1.56
     संबंध
    1.54
    дный
    1.52
    Activations Density 0.003%

    No Known Activations