© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14859
    Prev
    Next
    INDEX
    Explanations

    closing parentheses or code blocks

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

    This neuron detects Python function-definition signatures (the “def function_name(self, …):” lines).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    0.85
    ни
    0.82
    /*
    0.68
     checkFor
    0.67
    //!
    0.65
    if
    0.64
    //{
    0.64
     catatan
    0.64
    SimpleDateFormat
    0.63
    jPanel
    0.63
    POSITIVE LOGITS
    stantially
    0.78
    íny
    0.75
     raisins
    0.72
    lerinden
    0.71
    tey
    0.70
    šnj
    0.69
     vinaig
    0.69
    ই
    0.69
    llium
    0.68
     ἀ
    0.68
    Activations Density 0.000%

    No Known Activations