© 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. 34-GEMMASCOPE-RES-131K
    7. 47981
    Prev
    Next
    INDEX
    Explanations

    XML namespaces xsi and xsd

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

    The neuron strongly activates on tokens that contain digits or look like numeric/version identifiers (e.g. version numbers, dates, “E!”, “#”, XML attributes).

    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
    meg
    -0.81
    系の
    -0.73
     publiek
    -0.72
     título
    -0.72
     Codex
    -0.71
     ESI
    -0.71
     Vitale
    -0.71
     Mourning
    -0.71
    odori
    -0.70
     વ
    -0.69
    POSITIVE LOGITS
     TLC
    1.16
    TLC
    0.91
    mY
    0.85
     segmentos
    0.81
    Caesar
    0.75
    INFIN
    0.75
    Alas
    0.75
     Colt
    0.75
    IntegrationTest
    0.73
    áng
    0.72
    Activations Density 0.012%

    No Known Activations