© 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. 12006
    Prev
    Next
    INDEX
    Explanations

    market, motivating, sheep

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

    The neuron strongly lights up on content‐bearing words (i.e. non–function words like meaningful nouns, verbs, and adjectives) rather than on common little “glue” 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
     wurde
    0.73
     tidak
    0.70
     harus
    0.70
     c
    0.66
     non
    0.66
     have
    0.66
     can
    0.66
     essere
    0.66
     wurden
    0.64
     paese
    0.64
    POSITIVE LOGITS
     wholeheartedly
    0.72
    მასრულ
    0.72
    ثمار
    0.71
     선보
    0.71
    𝘵
    0.69
    NERVE
    0.68
     이어
    0.68
    มอบ
    0.67
    㑓
    0.67
    䉿
    0.67
    Activations Density 0.081%

    No Known Activations