© 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. 8077
    Prev
    Next
    INDEX
    Explanations

    code/programming syntax and symbols

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

    The neuron is picking out numeric literals (numbers and number‐like tokens) in code or markup.

    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
     for
    -1.29
     at
    -1.23
     so
    -0.90
     until
    -0.90
     after
    -0.90
     some
    -0.89
     in
    -0.85
    Even
    -0.85
     even
    -0.84
     what
    -0.83
    POSITIVE LOGITS
    ographers
    0.94
    Modelos
    0.90
     comical
    0.88
    Holo
    0.84
     accordo
    0.84
     morgue
    0.84
    designed
    0.83
    心里
    0.83
    miljø
    0.82
    alers
    0.82
    Activations Density 0.000%

    No Known Activations