© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66859
    Prev
    Next
    INDEX
    Explanations

    state or condition

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

    The neuron fires on prominent, domain-specific content words (technical or academic nouns and key terms) in formal, scholarly text.

    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
    voici
    -1.88
    Bises
    -1.82
    NOTAS
    -1.80
     burada
    -1.77
    ׳
    -1.73
    ֊
    -1.73
    桝
    -1.73
    没办法
    -1.73
     هنا
    -1.72
     pouze
    -1.67
    POSITIVE LOGITS
     on
    2.00
     first
    1.79
     not
    1.63
     people
    1.62
     usually
    1.58
     he
    1.56
     two
    1.55
    Czym
    1.55
     used
    1.53
     in
    1.50
    Activations Density 0.132%

    No Known Activations