© 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. 10-GEMMASCOPE-RES-131K
    7. 41606
    Prev
    Next
    INDEX
    Explanations

    code segments and variables

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

    The neuron activates whenever it encounters numeric literals (integer or floating-point 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_10/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
    -1.87
    This
    -1.81
    or
    -1.80
    -1.76
    <em>
    -1.72
    These
    -1.69
    {
    -1.66
    ness
    -1.66
    for
    -1.65
    6
    -1.64
    POSITIVE LOGITS
     generazione
    1.53
     conservazione
    1.52
     pourrait
    1.42
     continúa
    1.42
    犼
    1.41
     today
    1.41
     tentar
    1.41
    🪘
    1.39
     scoperta
    1.39
     menjadi
    1.39
    Activations Density 0.002%

    No Known Activations