© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15917
    Prev
    Next
    INDEX
    Explanations

    API call

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

    The neuron reliably lights up on the first “real” content word at the start of a new paragraph or section.

    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
     consequential
    0.83
    figured
    0.72
    ט
    0.71
    arang
    0.70
    financed
    0.69
    fontSize
    0.68
    ਏ
    0.68
    ́t
    0.68
    BusinessType
    0.68
    te
    0.67
    POSITIVE LOGITS
    い
    0.86
    レーション
    0.83
    ↵
    0.79
    ра
    0.77
    へと
    0.75
     devenu
    0.75
    ストラップ
    0.74
    begin
    0.73
    reicher
    0.72
    我
    0.72
    Activations Density 0.000%

    No Known Activations