© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89814
    Prev
    Next
    INDEX
    Explanations

    fish and fisheries

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

    content related to marine resources, fisheries, and sustainable aquatic ecosystems.

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

    The neuron is primarily detecting standalone numeric tokens (numbers) in the text.

    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
     IAP
    -0.77
    psies
    -0.72
    alló
    -0.72
    æa
    -0.69
     aged
    -0.69
     ложка
    -0.68
    拨
    -0.68
     Arts
    -0.67
     mone
    -0.67
     сторона
    -0.67
    POSITIVE LOGITS
     fisheries
    1.80
     fishing
    1.75
     fish
    1.59
    fishing
    1.59
    Fishing
    1.47
    fish
    1.44
     Fishing
    1.44
     Fisheries
    1.41
    Fisheries
    1.36
    tuna
    1.29
    Activations Density 0.008%

    No Known Activations