© 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. 7667
    Prev
    Next
    INDEX
    Explanations

    association agreement

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

    The neuron fires on semantically contentful words (non‐stopwords) such as nouns, verbs, adjectives, and other “important” tokens, but stays silent on common 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
    ર્સ
    0.77
     Traditions
    0.77
    िल्म
    0.76
     Illustrations
    0.74
     Mathematics
    0.73
     Sélection
    0.73
     Natives
    0.73
    鯽
    0.73
    ॉर्म
    0.71
     paraissent
    0.71
    POSITIVE LOGITS
    p
    1.01
    muster
    0.87
    phed
    0.84
    t
    0.82
    hok
    0.82
    \;
    0.81
    sighted
    0.81
    m
    0.80
    mrow
    0.79
    partner
    0.78
    Activations Density 0.001%

    No Known Activations