© 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. 35235
    Prev
    Next
    INDEX
    Explanations

    return find in code

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

    The neuron detects occurrences of the “find(” method call 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
     miró
    -0.88
    loga
    -0.87
     mód
    -0.86
     nedeniyle
    -0.84
    を楽し
    -0.83
    Ǐ
    -0.83
     riferimento
    -0.83
    ườ
    -0.82
     lograron
    -0.82
     próprias
    -0.81
    POSITIVE LOGITS
    后续
    0.87
    return
    0.84
    之间
    0.81
     next
    0.81
     Reaktion
    0.81
    下一步
    0.81
    Next
    0.79
    ซ์
    0.79
    后面的
    0.79
     medie
    0.79
    Activations Density 0.006%

    No Known Activations