© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13228
    Prev
    Next
    INDEX
    Explanations

    paleontology, omics, angiography

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

    academic and scientific fields or disciplines ending in "-ology" or "-omics".

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

    The neuron activates on long, domain‐specific nouns and labels—especially technical or proper‐name terms like Tolkien, DataAccess, ontology/ontological, “-omic” words (datomic, proteomic, multiomic), 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
    y
    -3.84
    胧
    -2.98
    蓠
    -2.81
    as
    -2.64
    ).
    -2.63
     are
    -2.44
    횃
    -2.38
    ić
    -2.34
     mencion
    -2.30
     роботи
    -2.28
    POSITIVE LOGITS
    ם
    2.97
    "
    2.53
    諼
    2.45
     наши
    2.38
    お昼
    2.28
    ᡵ
    2.23
    </em>
    2.19
     nouvelles
    2.16
    </strong>
    2.16
    很喜欢
    2.11
    Activations Density 0.018%

    No Known Activations