© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15996
    Prev
    Next
    INDEX
    Explanations

    function return value

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

    This neuron detects API or code‐documentation phrases that specify what a function returns (e.g. “returns a string,” “returns NULL,” etc.).

    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_31_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
     کسی
    0.62
     especificar
    0.62
     வயிற்றில்
    0.61
     terdapat
    0.59
    🇴
    0.58
     বাংলায়
    0.57
     बहुपद
    0.57
     Backend
    0.57
    bindParam
    0.56
     исто
    0.56
    POSITIVE LOGITS
     returns
    1.11
    return
    1.07
     return
    1.05
    returns
    1.00
    Returns
    1.00
     Returns
    0.99
    返回
    0.98
    返
    0.96
     Return
    0.94
     возвра
    0.93
    Activations Density 0.026%

    No Known Activations