© 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. 4803
    Prev
    Next
    INDEX
    Explanations

    app categories, general types, specific functions

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

    This neuron fires strongly on content-bearing words (especially nouns and other key open-class 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
    🔬
    0.77
     試験
    0.70
     ૧
    0.68
    ١
    0.68
    ⛈
    0.67
    🩸
    0.67
    $_
    0.66
     前回
    0.66
    🗡
    0.65
    Л
    0.65
    POSITIVE LOGITS
     showbiz
    0.99
     nightlife
    0.93
     commuter
    0.88
     franchising
    0.88
     togetherness
    0.88
     exclusivity
    0.88
     entertainment
    0.86
     multipurpose
    0.86
     concierge
    0.86
     commuters
    0.84
    Activations Density 1.212%

    No Known Activations