© 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. 22-GEMMASCOPE-RES-131K
    7. 68004
    Prev
    Next
    INDEX
    Explanations

    numeric and programming terms

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

    The neuron activates on numeric constants (literal numbers) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     люд
    -1.04
    cra
    -0.97
     προϊόν
    -0.91
     potency
    -0.87
    AFFIRMED
    -0.85
    owa
    -0.83
     subsequent
    -0.82
    oubtedly
    -0.82
     to
    -0.81
    WP
    -0.81
    POSITIVE LOGITS
    昔の
    0.88
     bolsillos
    0.88
     skriv
    0.85
     tornillos
    0.84
     hombro
    0.82
     cortos
    0.82
     carbono
    0.80
     lâ
    0.80
     verkligen
    0.80
     opravdu
    0.80
    Activations Density 0.004%

    No Known Activations