© 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. 10902
    Prev
    Next
    INDEX
    Explanations

    . * explanation

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

    The neuron fires on descriptive phrases that highlight distinctive visual or aesthetic background elements (especially retro or design‐oriented imagery).

    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
     लोकांनी
    0.64
    และความ
    0.59
    ㅄ
    0.58
    คนที่
    0.56
    ความ
    0.56
     consequent
    0.54
    ர்ப்பு
    0.54
     consequ
    0.54
    됬
    0.54
    ೨
    0.53
    POSITIVE LOGITS
     Likewise
    0.76
     Another
    0.73
     Similarly
    0.70
     aptly
    0.70
     Catania
    0.68
     Featuring
    0.67
     Selangor
    0.65
     Lastly
    0.64
     Semarang
    0.63
     Finally
    0.60
    Activations Density 0.038%

    No Known Activations