© 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. 12634
    Prev
    Next
    INDEX
    Explanations

    data structures and values

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

    The neuron activates on generic content nouns carrying informational weight (e.g. “information,” “data,” “water,” “found”).

    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
     มา
    0.62
    ussion
    0.61
    ティスト
    0.61
     شریف
    0.61
     बना
    0.59
     خط
    0.59
    ismes
    0.59
    㫣
    0.59
    datast
    0.58
     บริ
    0.58
    POSITIVE LOGITS
     superl
    0.57
     WF
    0.54
     readers
    0.54
     final
    0.53
     lat
    0.52
     manche
    0.52
     comparable
    0.51
     kei
    0.51
     regress
    0.49
     DF
    0.49
    Activations Density 0.000%

    No Known Activations