© 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. 110861
    Prev
    Next
    INDEX
    Explanations

    axon and Corbyn

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

    The neuron detects mentions of “axon” or its morphological variants (e.g. “axonal”).

    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
    鼍
    -2.86
     icônes
    -2.48
    felpa
    -2.45
     vetores
    -2.45
    抬手
    -2.42
    ቍ
    -2.42
     We
    -2.41
     sufri
    -2.41
     asust
    -2.36
     hadden
    -2.31
    POSITIVE LOGITS
    u
    3.17
    та
    2.97
    time
    2.78
    In
    2.69
    м
    2.56
    و
    2.55
     If
    2.52
     we
    2.48
    \
    2.42
    It
    2.41
    Activations Density 0.040%

    No Known Activations