© 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. 9537
    Prev
    Next
    INDEX
    Explanations

    proof of identity verification

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

    The neuron fires on formal obligation or requirement statements—especially those specifying “must,” “required,” or “should” along with numeric details (e.g. numbers of documents or criteria to be met).

    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
     alkalies
    0.57
    ὸ
    0.52
    recated
    0.51
     વિક
    0.50
    plyr
    0.49
     विशेषता
    0.48
    auan
    0.48
     ശിഷ്യ
    0.48
     素材
    0.48
    랏
    0.48
    POSITIVE LOGITS
     membayar
    0.63
     Signed
    0.60
     additionally
    0.59
     pledging
    0.59
     undergo
    0.59
     zudem
    0.59
     zusätzlich
    0.59
     inoltre
    0.58
     undergone
    0.58
     Pledge
    0.58
    Activations Density 0.174%

    No Known Activations