© 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. 22-GEMMASCOPE-RES-131K
    7. 14438
    Prev
    Next
    INDEX
    Explanations

    nitric oxide

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

    scientific or technical terms in academic/research papers.

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

    This neuron fires on longer, domain-specific content words (e.g. specialized technical or anatomical terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     régiment
    -1.11
    onResume
    -1.11
    "}";
    -1.10
     اصول
    -1.03
    又能
    -1.03
    (")");
    -1.01
     フリル
    -1.01
     chantier
    -0.98
     Dinas
    -0.97
     considérée
    -0.97
    POSITIVE LOGITS
     Алексей
    1.20
    Quite
    1.20
    いただきます
    1.10
     Игорь
    1.09
    There
    1.09
    dá
    1.07
     обычно
    1.07
    Almost
    1.07
    With
    1.05
    For
    1.05
    Activations Density 0.086%

    No Known Activations