© 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. 519
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on subjective evaluative adjectives (e.g. “good,” “fine,” “normal,” “bad”) that express an opinion or judgment.

    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
    and
    0.65
    而且
    0.62
    with
    0.60
    そして
    0.58
     وم
    0.58
     със
    0.58
    和
    0.57
    wwww
    0.55
    所有
    0.55
    และ
    0.54
    POSITIVE LOGITS
     neither
    0.61
     objection
    0.56
     либо
    0.56
     Çünkü
    0.55
     deoarece
    0.52
     sondern
    0.52
     dimethyl
    0.52
     произо
    0.52
    ,/*
    0.51
     anymore
    0.51
    Activations Density 0.163%

    No Known Activations