© 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. 40143
    Prev
    Next
    INDEX
    Explanations

    imports and initializations

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

    The neuron is strongly activated by numeric literals (digits) 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_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
     étui
    -1.13
     gän
    -1.11
     Heilige
    -1.05
     arrivant
    -1.01
    yní
    -0.98
     höl
    -0.96
    rénées
    -0.95
    wast
    -0.95
    ogical
    -0.94
     coloriage
    -0.94
    POSITIVE LOGITS
     at
    1.02
     могут
    0.96
    ampang
    0.94
    pova
    0.91
     can
    0.88
     должен
    0.86
    <0xAE>
    0.86
    ₫
    0.86
    早めに
    0.86
     on
    0.85
    Activations Density 0.011%

    No Known Activations