© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65168
    Prev
    Next
    INDEX
    Explanations

    glycogen synthase kinase or government service

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

    This neuron activates on alphanumeric technical identifiers (e.g. codes like “GS3536,” “GS4,” numeric strings, and similar catalog or registry numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    dams
    -0.83
     lagging
    -0.80
     leach
    -0.79
     töd
    -0.79
     OTO
    -0.79
    acciones
    -0.78
     fenó
    -0.78
    sklä
    -0.77
     halben
    -0.77
     Chom
    -0.77
    POSITIVE LOGITS
     GS
    1.35
    GS
    1.04
     gs
    0.93
    ばかり
    0.88
    gs
    0.77
     Gs
    0.77
     arrange
    0.73
     most
    0.72
    Gamma
    0.70
    Gs
    0.70
    Activations Density 0.035%

    No Known Activations