© 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. 22-GEMMASCOPE-RES-131K
    7. 14589
    Prev
    Next
    INDEX
    Explanations

    scientific taxonomies: -idae, -iformes

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

    taxonomic classifications and scientific names of species in biological classification systems.

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

    This neuron detects Latin taxonomic names (e.g. family, order, or genus names) in biological species descriptions.

    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
    ^(@
    -1.46
     your
    -1.44
     the
    -1.32
     masukan
    -1.30
    galkan
    -1.27
     launched
    -1.25
     on
    -1.25
     done
    -1.20
     easy
    -1.19
     additional
    -1.17
    POSITIVE LOGITS
    Bitcoin
    1.66
     зарубе
    1.39
    Tuesday
    1.39
    Χ
    1.34
    France
    1.30
    THEY
    1.28
    Γ
    1.25
    GST
    1.24
    Iran
    1.24
    French
    1.24
    Activations Density 0.037%

    No Known Activations