© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4576
    Prev
    Next
    INDEX
    Explanations

    you know

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

    The neuron fires on personal/pronominal reference words (e.g. I, you, it, they) that mark speaker or addressee involvement.

    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_24_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
     הער
    0.64
    ,\\
    0.61
     Архивная
    0.61
     unimplemented
    0.58
    ့်
    0.56
    \_
    0.56
     wilderness
    0.54
     在
    0.54
     Wellesley
    0.54
     今天
    0.53
    POSITIVE LOGITS
    disp
    0.61
    pharmac
    0.60
     créée
    0.60
    create
    0.59
    placed
    0.59
    contacto
    0.59
    posto
    0.59
    conta
    0.57
     creato
    0.56
    ടുത
    0.56
    Activations Density 0.081%

    No Known Activations