© 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. 11323
    Prev
    Next
    INDEX
    Explanations

    listing categories and considerations

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

    The neuron responds to content‐bearing keywords (substantive topic terms) rather than to 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
     and
    0.82
    和一个
    0.80
    and
    0.77
    并且
    0.76
    지와
    0.75
    並且
    0.74
    和
    0.74
     I
    0.73
     And
    0.72
     এবং
    0.72
    POSITIVE LOGITS
     lainnya
    1.09
     miscellaneous
    0.97
    อื่นๆ
    0.93
    その他
    0.86
     інших
    0.85
    各类
    0.83
     termasuk
    0.82
     outras
    0.81
     incluyendo
    0.81
     각종
    0.81
    Activations Density 1.413%

    No Known Activations