© 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. 13702
    Prev
    Next
    INDEX
    Explanations

    introduction to lists

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

    The neuron strongly fires on the first few content words of major sentences (i.e. marking sentence or thought boundaries).

    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
     smears
    0.60
     ,
    0.59
     też
    0.57
     velvety
    0.55
     时
    0.55
     tormented
    0.55
     ،
    0.54
    ával
    0.54
     (~
    0.54
    ayy
    0.53
    POSITIVE LOGITS
     Namely
    1.13
    那就是
    1.13
    一是
    1.13
     namely
    1.12
    namely
    1.09
     nämlich
    1.05
     yaitu
    1.03
     namelijk
    0.98
    Firstly
    0.93
     факторы
    0.93
    Activations Density 0.644%

    No Known Activations