© 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. 12607
    Prev
    Next
    INDEX
    Explanations

    investment of recipient client

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

    The neuron strongly activates on the first content token of a new section or list item—i.e. standalone headings or single-word “bullet” entries at the start of a line.

    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
    цом
    0.86
    эг
    0.70
     literals
    0.70
    膩
    0.69
     سیس
    0.69
     मैती
    0.69
     diagnoses
    0.68
    གྲ
    0.68
    စု
    0.68
    Ⲩ
    0.68
    POSITIVE LOGITS
     ono
    0.81
    vär
    0.76
    la
    0.73
    ي
    0.73
    vant
    0.72
    pä
    0.72
    y
    0.71
     nedenle
    0.70
    ski
    0.68
    pura
    0.68
    Activations Density 0.000%

    No Known Activations