© 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. 60254
    Prev
    Next
    INDEX
    Explanations

    so [adjective]

    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
    Արտաքին
    -2.30
    趼
    -1.91
    
    -1.88
    骉
    -1.86
    摇了
    -1.83
    蛲
    -1.80
     acompañada
    -1.77
     hogyan
    -1.77
    ’,
    -1.74
     sentada
    -1.73
    POSITIVE LOGITS
     that
    2.39
     they
    1.96
    6
    1.78
     are
    1.61
     other
    1.59
     others
    1.55
    1
    1.48
     it
    1.48
    Physician
    1.48
    4
    1.46
    Activations Density 0.013%

    No Known Activations