© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65868
    Prev
    Next
    INDEX
    Explanations

    function initialization or configuration

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

    The neuron activates on numeric literal tokens (i.e. numbers) in code.

    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
     journaliste
    -1.85
    馓
    -1.82
     chanteur
    -1.77
    camisa
    -1.70
    罴
    -1.67
     protože
    -1.66
    繙
    -1.64
     interesan
    -1.60
    螃
    -1.60
    厛
    -1.58
    POSITIVE LOGITS
    i
    2.17
    y
    1.93
    to
    1.93
    x
    1.81
    c
    1.74
    p
    1.73
    N
    1.72
     they
    1.66
    n
    1.65
    j
    1.65
    Activations Density 0.006%

    No Known Activations