© 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. 12733
    Prev
    Next
    INDEX
    Explanations

    molecule A-to-D, water molecules, morning and night

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

    The neuron fires most strongly on semantically rich content words—especially longer verbs and nouns—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
    en
    0.89
    deploy
    0.80
    wayne
    0.76
    emir
    0.75
    deployment
    0.74
    call
    0.73
    warn
    0.73
    ˝
    0.71
    s
    0.71
    check
    0.70
    POSITIVE LOGITS
    公民
    0.86
    кую
    0.81
    хом
    0.81
    ବା
    0.80
    カジュアル
    0.79
    ਟ
    0.79
    ⿹
    0.79
     envisioned
    0.78
    攵
    0.77
    ріа
    0.76
    Activations Density 0.000%

    No Known Activations