© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1839
    Prev
    Next
    INDEX
    Explanations

    preferences and materials

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

    The neuron detects salient topic‐or category-indicative nouns (e.g. “podcasts,” “music,” “textiles,” “hospitals,” “fiber,” 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
     And
    0.88
     并
    0.88
    并且
    0.83
     並
    0.83
    並且
    0.80
    And
    0.80
    并
    0.80
     거고
    0.77
     oppure
    0.77
    幷
    0.76
    POSITIVE LOGITS
    、
    1.55
     、
    1.16
    ﹑
    1.13
    、「
    0.97
    、『
    0.93
     உள்ளிட்ட
    0.91
    、$
    0.87
     وغيرها
    0.87
     등의
    0.84
    、【
    0.84
    Activations Density 0.527%

    No Known Activations