© 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. 12807
    Prev
    Next
    INDEX
    Explanations

    breadth, depth, or thickness

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

    The neuron is a paragraph‐boundary detector—it strongly activates on the first content word of each new section or paragraph.

    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
     имена
    0.92
     bosses
    0.81
    इसके
    0.80
    𝚄
    0.79
     frauds
    0.79
     acced
    0.77
     instruments
    0.76
     counsell
    0.76
     conséquent
    0.75
     artistes
    0.75
    POSITIVE LOGITS
    на
    0.83
    m
    0.80
     طلعت
    0.79
    ig
    0.75
    objeto
    0.75
    ைட்
    0.75
    ak
    0.74
     वेरिएबल
    0.74
    plaats
    0.73
    platten
    0.73
    Activations Density 0.000%

    No Known Activations