© 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. 22-GEMMASCOPE-RES-131K
    7. 130498
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric literals (integer and decimal constants) in the code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     if
    -1.45
     when
    -1.29
     just
    -1.19
    Enllaços
    -1.15
     each
    -1.08
     from
    -1.06
    臵
    -1.04
     every
    -1.03
    хані
    -1.03
    してみてください
    -1.02
    POSITIVE LOGITS
    public
    1.09
    ↵↵↵
    1.09
    ↵↵
    1.09
    private
    1.08
     andere
    1.07
    の家
    0.99
    strncmp
    0.99
     szeret
    0.96
     estadía
    0.94
     zapatos
    0.94
    Activations Density 0.013%

    No Known Activations