© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3217
    Prev
    Next
    INDEX
    Explanations

    albums and

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

    The neuron activates on individual content nouns—especially concrete or key entity words (e.g. “trees,” “email,” “cost,” “frame”)—effectively picking out important nouns in the text.

    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
    最重要的
    0.69
     गेंदबाजी
    0.66
    るとき
    0.66
     जानना
    0.66
    잦
    0.64
    说法
    0.63
    ẹt
    0.63
    ための
    0.62
    ల్ని
    0.62
    れている
    0.62
    POSITIVE LOGITS
     or
    1.23
     или
    1.20
     hoặc
    1.20
     অথবা
    1.16
     หรือ
    1.12
    หรือ
    1.11
     atau
    1.08
     ή
    1.08
     alebo
    1.08
     또는
    1.07
    Activations Density 1.179%

    No Known Activations