© 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. 5868
    Prev
    Next
    INDEX
    Explanations

    daño y acidification

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

    The neuron selectively activates on semantically “content‐heavy” tokens—i.e. topical, domain‐specific nouns and adjectives (especially less common or technical terms) rather than on 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
     регистра
    0.74
     Саша
    0.68
     handsets
    0.67
     lathes
    0.66
     cuyas
    0.65
     ২০
    0.64
     નાના
    0.64
    㭜
    0.64
     печа
    0.64
     гульнявыя
    0.64
    POSITIVE LOGITS
     only
    0.76
     integration
    0.72
     purely
    0.71
     (
    0.71
     assim
    0.70
     arguably
    0.69
     un
    0.68
    un
    0.65
     uniquement
    0.64
    作为一个
    0.64
    Activations Density 0.243%

    No Known Activations