© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128221
    Prev
    Next
    INDEX
    Explanations

    zygomatic, mography

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

    biological terms related to zygotes and genetic components, particularly those with prefixes or roots like "zygo-", "zyga-", and "zygom-".

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

    The neuron selectively activates on occurrences of the letter sequence “zyg” (as in zygote, zygomatic, heterozygote, etc.).

    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
    '
    -1.75
    返
    -1.59
    亖
    -1.57
    ahh
    -1.55
    lección
    -1.55
    ет
    -1.55
    INTAIN
    -1.54
     mentioning
    -1.54
     is
    -1.53
    нию
    -1.52
    POSITIVE LOGITS
    ܜ
    2.14
    蘗
    1.62
     Hmmm
    1.61
     Almost
    1.61
    企业的
    1.61
     آید
    1.61
    
    1.60
    诸多
    1.58
    当时的
    1.58
     Perhaps
    1.55
    Activations Density 0.009%

    No Known Activations