© 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. 84390
    Prev
    Next
    INDEX
    Explanations

    darwin, azure, underpinning, dispatch

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

    This neuron activates on distinct named entities and specialized technical or biomedical terms (e.g., person names, place names, product/technology names, drug names).

    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
    nienie
    -2.64
    itized
    -2.44
    骉
    -2.38
     mauva
    -2.36
    薷
    -2.34
    
    -2.27
    ⚢
    -2.27
    佷
    -2.25
    ли
    -2.22
     промышлен
    -2.20
    POSITIVE LOGITS
    b
    3.31
    r
    3.02
    生活的
    2.91
    d
    2.84
     dzięki
    2.61
     Their
    2.55
    ?!?
    2.50
    y
    2.48
    
    2.47
    re
    2.42
    Activations Density 0.017%

    No Known Activations