© 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. 5817
    Prev
    Next
    INDEX
    Explanations

    understanding or knowing

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

    The neuron responds strongly to verbs (including lexical verbs and modals).

    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
    器
    0.54
     Luke
    0.54
    ವರಿ
    0.53
    CameraController
    0.53
    Luke
    0.52
     Darrell
    0.52
    bur
    0.51
    ்க்க
    0.51
     Moment
    0.51
     අව
    0.50
    POSITIVE LOGITS
     ហើយ
    0.86
    🤗
    0.80
     🙂
    0.80
     :)
    0.79
     😉
    0.78
     ;-)
    0.78
     поскольку
    0.77
     ;)
    0.77
     🤗
    0.76
    !
    0.74
    Activations Density 0.316%

    No Known Activations