© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1079
    Prev
    Next
    INDEX
    Explanations

    AI language model and lists

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

    This neuron detects terms related to quantitative market‐research reporting (e.g. “key,” “factors,” “trends,” “statistics,” “data,” “analysis,” “vendors,” “estimation”).

    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
     fledgling
    0.61
     cheerleader
    0.59
     empezar
    0.59
     alguma
    0.58
     ragazza
    0.58
     দ্যা
    0.57
    ﹗
    0.57
    英语
    0.57
     cordless
    0.56
     housework
    0.56
    POSITIVE LOGITS
     که
    0.94
     जो
    0.94
     जिसमें
    0.93
     which
    0.91
     που
    0.86
    which
    0.82
     whose
    0.81
     التي
    0.80
     që
    0.79
    ที่มี
    0.79
    Activations Density 0.122%

    No Known Activations