© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69503
    Prev
    Next
    INDEX
    Explanations

    researchers and professionals

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

    The neuron strongly activates on content‐rich, domain‐specific technical terms (nouns and adjectives) characteristic of formal academic or scientific writing.

    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
     conferencias
    -2.05
     военных
    -2.00
    harapkan
    -1.97
     aparatos
    -1.97
     capuz
    -1.96
    絝
    -1.94
     llavero
    -1.85
     faldas
    -1.84
     deportivas
    -1.83
     estuche
    -1.82
    POSITIVE LOGITS
    歟
    2.55
    2.45
    恚
    2.17
    踔
    2.17
    欤
    1.97
     меда
    1.88
     and
    1.87
    亟
    1.84
    !
    1.78
    怦
    1.78
    Activations Density 40.152%
    No Known Activations