© 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. 6137
    Prev
    Next
    INDEX
    Explanations

    agreement outlining

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

    The neuron detects boilerplate legal and copyright/terms-of-use language in text.

    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
     istem
    0.58
     suspect
    0.52
    ximately
    0.52
     kics
    0.52
     bébé
    0.50
     wicked
    0.49
     हाईकोर्ट
    0.49
    ኸ
    0.49
     Sus
    0.48
    quinoxaline
    0.48
    POSITIVE LOGITS
    खाली
    0.56
    zyg
    0.55
    ുകള
    0.54
     કરોડ
    0.51
    །
    0.51
    ilation
    0.50
    ﭥ
    0.48
    倉
    0.48
    ítico
    0.46
     প্রতিবেদক
    0.46
    Activations Density 0.164%

    No Known Activations