© 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. 34-GEMMASCOPE-RES-131K
    7. 1618
    Prev
    Next
    INDEX
    Explanations

    OSHA, CFR, Silica, scaffold

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

    legal and regulatory document content, particularly when referencing codes, regulations, and standards.

    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_34/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
     gods
    -0.72
     bolster
    -0.72
    colnshire
    -0.71
    stype
    -0.70
     cyclo
    -0.69
     menú
    -0.69
    rdr
    -0.69
    rogate
    -0.68
     ir
    -0.68
    colate
    -0.68
    POSITIVE LOGITS
     OSHA
    1.23
    OSHA
    0.93
     HAZ
    0.87
    Sca
    0.87
    EAP
    0.81
    WILLIAM
    0.80
    scaffold
    0.79
     EAP
    0.78
     CFR
    0.77
    Scaffold
    0.77
    Activations Density 0.014%

    No Known Activations