© 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. 10710
    Prev
    Next
    INDEX
    Explanations

    sulfate, Bosnia, Anatomy, Dixie

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects chemical compounds with "sulfate" in their name, particularly in scientific or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     They
    -2.81
     beeindruck
    -2.73
    鬭
    -2.61
    ronesia
    -2.52
    各样的
    -2.50
    
    -2.48
    鷓
    -2.47
     allzu
    -2.38
     unangemess
    -2.38
    ⇹
    -2.34
    POSITIVE LOGITS
    s
    4.22
    e
    3.14
    re
    3.00
    ta
    2.84
    isation
    2.80
    }
    2.73
    i
    2.66
     contento
    2.63
     they
    2.61
    ا
    2.58
    Activations Density 0.011%

    No Known Activations