© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7894
    Prev
    Next
    INDEX
    Explanations

    durations of time

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

    The neuron strongly activates on scientific or Latin‐style chemical and botanical ingredient names (e.g. compounds listed in a product’s “Ingredients” or “Shade” list).

    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
     específicos
    0.94
     midfielders
    0.94
     filmpje
    0.93
     documentos
    0.90
     девя
    0.86
    bym
    0.84
    пы
    0.83
    ւ
    0.83
     ninguém
    0.81
     especialistas
    0.80
    POSITIVE LOGITS
     Бі
    0.78
    ’
    0.78
     البي
    0.76
     M
    0.74
     BIB
    0.73
     النموذج
    0.73
     U
    0.71
     Project
    0.70
     L
    0.70
     C
    0.68
    Activations Density 0.000%

    No Known Activations