© 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. 24-GEMMASCOPE-2-RES-16K
    7. 10282
    Prev
    Next
    INDEX
    Explanations

    only intelligent people

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

    This neuron strongly activates on formal legal or regulatory terminology (e.g. words like “jurisdiction,” “liability,” “warranty,” “law”).

    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
    ot
    0.75
    ined
    0.75
    ian
    0.71
    ap
    0.70
    ip
    0.70
    iterranean
    0.68
     $
    0.66
    ia
    0.66
    en
    0.65
    op
    0.65
    POSITIVE LOGITS
     appelez
    1.01
     adhé
    0.98
     perasaan
    0.92
     ondas
    0.91
    汰
    0.91
     allez
    0.89
     powerAll
    0.87
     guérir
    0.85
     ribu
    0.85
     quels
    0.84
    Activations Density 0.000%

    No Known Activations