© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109452
    Prev
    Next
    INDEX
    Explanations

    opening quote/delimiter

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

    The neuron fires on numeric literal tokens (integer constants) in code or 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_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
     just
    -1.87
     what
    -1.81
     any
    -1.73
     those
    -1.73
     first
    -1.70
     out
    -1.69
     other
    -1.66
     almost
    -1.66
     make
    -1.66
     Those
    -1.66
    POSITIVE LOGITS
     Dinas
    1.80
     terrific
    1.56
     quintessential
    1.55
     boister
    1.55
     horrid
    1.55
     ſever
    1.55
     captivating
    1.54
     colossal
    1.54
     delightfully
    1.52
     alho
    1.52
    Activations Density 0.035%

    No Known Activations