© 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. 19380
    Prev
    Next
    INDEX
    Explanations

    integer declarations

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

    The neuron activates on integer numeric literals 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
    iſter
    -1.84
    𓁹
    -1.79
    烀
    -1.74
    almost
    -1.73
    provides
    -1.73
     mogli
    -1.70
    nearly
    -1.70
    抨
    -1.69
     ceux
    -1.67
    孥
    -1.64
    POSITIVE LOGITS
     this
    1.73
     which
    1.71
    后再
    1.63
     However
    1.62
     Also
    1.62
    といけない
    1.56
     Some
    1.51
     is
    1.50
     although
    1.50
     една
    1.48
    Activations Density 0.030%

    No Known Activations