© 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. 1831
    Prev
    Next
    INDEX
    Explanations

    new

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

    The neuron activates on the adjective “new,” flagging instances where something is being introduced as new.

    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
     Algunas
    0.90
    が存在
    0.86
    の場合は
    0.80
    おり
    0.80
     области
    0.79
    ссы
    0.78
     существо
    0.77
    戙
    0.76
    했던
    0.76
    </tr>
    0.75
    POSITIVE LOGITS
     york
    1.08
    swire
    1.08
    york
    1.07
     zealand
    1.07
     प्रस्तावित
    1.03
    foundland
    1.02
     सिरे
    1.00
     नवे
    0.97
    fang
    0.93
    comer
    0.87
    Activations Density 0.056%

    No Known Activations