© 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. 22-GEMMASCOPE-RES-131K
    7. 71005
    Prev
    Next
    INDEX
    Explanations

    biological classification prefixes

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

    taxonomic names of organisms, particularly scientific species names.

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

    This neuron detects mentions of organisms or taxonomic names (e.g., species, genus, and higher‐level taxa).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     décontract
    -1.27
    viembre
    -1.25
     Bakterien
    -1.24
    🦿
    -1.22
    ︲
    -1.15
     lanzó
    -1.13
    旁边
    -1.12
     diputados
    -1.09
    viendo
    -1.08
     chaves
    -1.07
    POSITIVE LOGITS
     still
    1.16
    cended
    1.16
    specific
    1.13
     specific
    1.09
    Ʋ
    1.08
     gelas
    1.06
    irmer
    1.05
    توضیحات
    1.05
     unique
    1.04
    ☭
    1.04
    Activations Density 0.310%

    No Known Activations