© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 9697
    Prev
    Next
    INDEX
    Explanations

    python imports

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

    This neuron detects mentions of software libraries or modules (i.e. package or module names).

    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
    /
    0.63
    </body>
    0.62
    <
    0.61
    </
    0.61
    For
    0.60
    for
    0.59
    Excluded
    0.58
    出现
    0.57
    จะไม่
    0.56
    :
    0.56
    POSITIVE LOGITS
     ".",
    0.70
     reagents
    0.63
     ['(?
    0.61
     argparse
    0.61
     matematik
    0.61
     soups
    0.59
     algorithms
    0.58
     ਅਤੇ
    0.57
     ReturnVal
    0.57
     itertools
    0.57
    Activations Density 0.026%

    No Known Activations