© 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. 10199
    Prev
    Next
    INDEX
    Explanations

    code generation requests

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

    This neuron detects newswire dateline and source‐label tokens (e.g. all-caps locations, “(AP)”, and the surrounding dashes).

    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
     tersebut
    0.55
    该
    0.53
     outsourced
    0.49
    もあった
    0.48
     relatable
    0.47
     ایش
    0.46
     nearby
    0.46
     medias
    0.46
    此
    0.46
    けれ
    0.46
    POSITIVE LOGITS
     Coroner
    0.56
     ممکن
    0.52
     可能
    0.51
    credi
    0.50
     追加
    0.50
     confirmó
    0.50
    
    0.50
     Likely
    0.48
     গেলেন
    0.47
     pourrait
    0.47
    Activations Density 0.112%

    No Known Activations