© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 579
    Prev
    Next
    INDEX
    Explanations

    environmental compliance and regulations

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

    legal and regulatory text, especially in government and environmental documents.

    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
    asteroid
    -0.79
     įva
    -0.77
     に関する
    -0.75
     Psychic
    -0.75
    mesin
    -0.73
    醜
    -0.71
    几个
    -0.71
     sprend
    -0.70
     camouflage
    -0.69
    /');
    -0.68
    POSITIVE LOGITS
     EPA
    0.95
    TSCA
    0.93
     anthropogenic
    0.88
     capacitor
    0.84
     Анна
    0.81
     escalate
    0.80
     ambiental
    0.78
    liflower
    0.78
    rukt
    0.76
     ambient
    0.75
    Activations Density 0.010%

    No Known Activations