© 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. 10-GEMMASCOPE-RES-131K
    7. 9662
    Prev
    Next
    INDEX
    Explanations

    bovine

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

    references to bovine (cow/cattle) subjects in scientific and medical contexts.

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

    The neuron fires on content words naming mammals—e.g. “hombre”/“homme” for human or “bovine” for cattle.

    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
     demonios
    -2.80
    一個
    -2.70
     unſ
    -2.52
     muelle
    -2.50
    絎
    -2.42
     agujero
    -2.38
    ほんとに
    -2.31
     пять
    -2.30
     acuario
    -2.30
    樒
    -2.28
    POSITIVE LOGITS
    al
    3.14
    𖥧
    2.84
     Also
    2.47
     THE
    2.36
    m
    2.36
     This
    2.33
     AND
    2.31
    le
    2.30
    er
    2.28
     незавер
    2.25
    Activations Density 0.002%

    No Known Activations