© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 6383
    Prev
    Next
    INDEX
    Explanations

    "what is" questions

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

    The neuron fires on words that signal authoritative statements or expert judgment (e.g. “true,” “corrected,” “nutritionists,” “health experts,” “parole,” 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
     、,
    0.84
     .,
    0.75
     ,
    0.75
     .(
    0.71
     ..,
    0.71
     €,
    0.68
                         
    0.67
                           
    0.66
    %、
    0.66
     $,
    0.66
    POSITIVE LOGITS
    But
    1.06
    However
    1.03
    Unfortunately
    0.97
    Now
    0.94
    Nevertheless
    0.93
    While
    0.92
    This
    0.90
    Sadly
    0.89
    Instead
    0.88
    Nowadays
    0.88
    Activations Density 0.058%

    No Known Activations