© 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. 22-GEMMASCOPE-RES-131K
    7. 13089
    Prev
    Next
    INDEX
    Explanations

    Joel's name followed by various contexts

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

    The neuron strongly activates on guillemet characters (the « symbol) appearing in the 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_22/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
     unrelenting
    -3.02
    ではまた
    -2.72
    七夕
    -2.42
     multifaceted
    -2.42
     plethora
    -2.41
     Almost
    -2.38
     impeccable
    -2.38
     incessant
    -2.36
     Before
    -2.36
     seven
    -2.36
    POSITIVE LOGITS
    ar
    3.05
    ть
    2.81
    to
    2.73
    which
    2.70
     WHICH
    2.61
     decidedly
    2.61
    \
    2.58
    鲠
    2.56
    Ꮅ
    2.53
    at
    2.52
    Activations Density 0.002%

    No Known Activations