© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16391
    Prev
    Next
    INDEX
    Explanations

    variable declarations and comparisons

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

    The neuron picks out numeric literals (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_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
     some
    -1.36
    中国的
    -1.30
    怎样的
    -1.29
    鞑
    -1.28
     else
    -1.27
    马来
    -1.27
     just
    -1.25
     any
    -1.20
     marat
    -1.16
    かげ
    -1.13
    POSITIVE LOGITS
    ('
    1.58
     intrigu
    1.48
    ୪
    1.44
    ጺ
    1.43
     Somewhat
    1.37
     Vorbe
    1.37
    "-
    1.36
     bestimm
    1.35
     Importantly
    1.34
    ,"
    1.34
    Activations Density 0.005%

    No Known Activations