© 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. 33391
    Prev
    Next
    INDEX
    Explanations

    commercial harvesting and production

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

    The neuron activates on formal taxonomic or species‐description language—that is, phrases used in scientific definitions of a species.

    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
     incubated
    -0.81
     موسي
    -0.78
     botanical
    -0.76
     avance
    -0.74
     malo
    -0.73
     доба
    -0.72
     Ammon
    -0.71
    vima
    -0.71
     potato
    -0.71
    ubation
    -0.69
    POSITIVE LOGITS
     catch
    1.85
     catches
    1.77
     caught
    1.49
     harvest
    1.41
    Harvest
    1.32
     commercial
    1.30
    Commercial
    1.23
    catch
    1.22
    commercial
    1.21
    COMMERCIAL
    1.21
    Activations Density 0.028%

    No Known Activations