© 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. 50268
    Prev
    Next
    INDEX
    Explanations

    international characters or code delimiters

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

    The neuron fires on numeric tokens—i.e. any standalone digit or digit‐containing string such as version numbers, charset values, array sizes, etc.

    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
    悦
    -0.87
    異なります
    -0.80
     atitude
    -0.77
    襖
    -0.75
     integrate
    -0.75
    grains
    -0.74
    鰭
    -0.73
     integrated
    -0.72
     accessories
    -0.71
     analysis
    -0.70
    POSITIVE LOGITS
     представлены
    0.82
    aino
    0.81
    itai
    0.79
     allora
    0.76
     deta
    0.76
    かなかった
    0.75
    多么
    0.72
    ◤
    0.72
     WJ
    0.72
    gesch
    0.71
    Activations Density 0.001%

    No Known Activations