© 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. 10-GEMMASCOPE-RES-131K
    4. 86960
    Prev
    Next
    INDEX
    Explanations

    biological species names

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

    Latin scientific names of plant and animal species.

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

    The neuron is triggered by fragments of Latin binomial species names (genus and species epithets).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -1.80
     each
    -1.68
     a
    -1.67
     their
    -1.67
     the
    -1.60
     it
    -1.55
     mereka
    -1.51
    にほんブログ村
    -1.45
     an
    -1.45
    ются
    -1.40
    POSITIVE LOGITS
    Ḏ
    1.66
     necesarios
    1.58
     mármol
    1.52
     already
    1.43
    bảng
    1.41
     его
    1.40
     üblichen
    1.38
     ścian
    1.36
    Ẓ
    1.34
    livejournal
    1.31
    Activations Density 0.129%

    No Known Activations