© 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. 7113
    Prev
    Next
    INDEX
    Explanations

    proper nouns and abbreviations

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

    The neuron fires on mentions of software product or tool names (e.g. IDEs, frameworks, services).

    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
     Они
    -1.55
     ними
    -1.50
    They
    -1.48
     они
    -1.42
     They
    -1.38
     Schriftsteller
    -1.36
    太多了
    -1.34
     аккуратно
    -1.33
     Sometimes
    -1.30
    Perhaps
    -1.30
    POSITIVE LOGITS
     its
    2.53
     to
    1.62
    出了一
    1.43
    Its
    1.43
     aktiviteter
    1.40
     itself
    1.39
    急忙
    1.38
    -
    1.38
    its
    1.30
    着一
    1.30
    Activations Density 0.195%

    No Known Activations