© 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. 10-GEMMASCOPE-RES-131K
    7. 60457
    Prev
    Next
    INDEX
    Explanations

    zygomatic, zymogen, zygote, zymosan

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

    words beginning with 'zy', particularly in scientific or technical contexts.

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

    This neuron detects tokens containing the letter sequence “zy.”

    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
    柺
    -2.73
    姩
    -2.61
    
    -2.58
     tetapi
    -2.55
    OUTUBE
    -2.50
     gustaMe
    -2.50
    族的
    -2.45
     offrent
    -2.44
    ῞
    -2.44
    pecabe
    -2.41
    POSITIVE LOGITS
    <
    3.63
    [
    3.53
    \\
    3.20
    *
    3.19
    e
    3.05
    —
    2.98
    i
    2.97
    ed
    2.97
    |
    2.89
    >
    2.81
    Activations Density 0.006%

    No Known Activations