© 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. 71921
    Prev
    Next
    INDEX
    Explanations

    list, multiple, for loops, arrays

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

    The neuron activates on numerical literals (numbers) in the 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
    三郎
    -0.84
    设定
    -0.78
     first
    -0.77
    settings
    -0.76
     settings
    -0.75
     penultimate
    -0.74
     Feature
    -0.73
     יְ
    -0.73
     changes
    -0.72
    distance
    -0.71
    POSITIVE LOGITS
     list
    1.13
     multiple
    1.05
    getJSONArray
    0.95
    querySelectorAll
    0.95
    писок
    0.93
    眯
    0.90
    OneToMany
    0.90
     multiplicity
    0.89
    multiple
    0.89
     múltip
    0.89
    Activations Density 0.228%

    No Known Activations