© 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. 91807
    Prev
    Next
    INDEX
    Explanations

    agriculture and research news

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

    agricultural and university-related content, particularly text related to farming, crops, and academic research.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on technical metadata and formatting elements—especially URLs, domain name fragments, and numeric identifiers in headers or citations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     період
    -0.82
    螢
    -0.80
    hunting
    -0.79
    versal
    -0.79
    χος
    -0.77
     кілька
    -0.76
    Nursing
    -0.76
    萤
    -0.75
    ົ
    -0.75
     Brahmin
    -0.74
    POSITIVE LOGITS
     publications
    0.87
    Doll
    0.85
     piaci
    0.84
     management
    0.84
     profitability
    0.81
     فرص
    0.81
     Dollars
    0.79
     publication
    0.79
    pubs
    0.79
     Gemüse
    0.78
    Activations Density 0.045%

    No Known Activations