© 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. 71999
    Prev
    Next
    INDEX
    Explanations

    list and array conversions

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

    The neuron is detecting programming identifiers and operators in code (e.g. variable names like `var`/`list` and symbols like `+`).

    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
    店で
    -1.05
    aporan
    -0.91
     name
    -0.91
    هرة
    -0.91
    gène
    -0.90
    intah
    -0.90
    InjectMocks
    -0.90
    ል
    -0.88
    mmate
    -0.88
    قاط
    -0.88
    POSITIVE LOGITS
    ⅾ
    1.07
     chanh
    1.00
    عالی
    0.96
    鈥
    0.96
    '}>
    0.94
    IAI
    0.94
    儇
    0.93
    FAQs
    0.93
    чних
    0.92
    Went
    0.91
    Activations Density 0.015%

    No Known Activations