© 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. 12219
    Prev
    Next
    INDEX
    Explanations

    biological species descriptions

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

    taxonomic descriptions of species, particularly in phrases like "is a species of" followed by the organism type.

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

    This neuron detects taxonomic definition sentences of the form “X is a species of Y (in the family Z),” i.e. organism classification statements.

    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
    Montag
    -0.77
     major
    -0.77
     inconvenient
    -0.75
    五郎
    -0.74
     شدند
    -0.73
     Seitz
    -0.72
    inetto
    -0.72
    itens
    -0.71
     الأكثر
    -0.71
    Aries
    -0.71
    POSITIVE LOGITS
     insects
    1.14
     bakteri
    0.98
     flowering
    0.91
     незавершена
    0.91
     fungi
    0.90
     insect
    0.88
     bacteria
    0.87
    ка
    0.86
    STRUCTIONS
    0.85
     belongs
    0.84
    Activations Density 0.098%

    No Known Activations