© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58306
    Prev
    Next
    INDEX
    Explanations

    oropharyngeal and nasopharyngeal

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

    scientific terminology with the prefix "oph-" and similar molecular/genetic terms.

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

    The neuron flags highly technical scientific terminology—especially domain-specific acronyms (e.g. ALEPH, ORF) and jargon-laden tokens.

    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
    u
    -3.02
    om
    -3.02
    et
    -2.61
    at
    -2.55
    ar
    -2.55
    1
    -2.52
    -
    -2.47
     podem
    -2.44
     '
    -2.42
    ng
    -2.41
    POSITIVE LOGITS
    𓋼
    2.67
    ⚋
    2.42
    醅
    2.39
    砹
    2.33
    ,’
    2.33
     eleva
    2.28
     pascua
    2.25
    ※※
    2.25
     memasak
    2.25
    趼
    2.23
    Activations Density 0.028%

    No Known Activations