© 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. 16319
    Prev
    Next
    INDEX
    Explanations

    to be

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

    The neuron identifies semantically “heavy” content words—i.e. key nouns and main verbs (especially formal or technical/legal terms) rather than light function words.

    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
     주어진
    0.73
    Từ
    0.73
     Δια
    0.72
     聞
    0.68
    Sebagai
    0.66
     Đối
    0.65
     Бен
    0.64
     Ancak
    0.62
     বণিক
    0.62
     从
    0.61
    POSITIVE LOGITS
     actually
    0.65
     tenido
    0.65
     estará
    0.64
    actually
    0.62
     tendrán
    0.61
     tendrá
    0.61
     देखेंगे
    0.60
    也会
    0.60
     mutlaka
    0.59
     precisa
    0.59
    Activations Density 0.368%

    No Known Activations