© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10375
    Prev
    Next
    INDEX
    Explanations

    YAML structure for resource `name`

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

    The neuron flags structural or formatting markers—things like opening quotation marks, numbered‐step labels, list dashes, and similar tokens that demarcate headings or list items.

    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_31_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
    {\"
    0.54
     ராஜ
    0.53
    
    0.52
    поло
    0.52
     equity
    0.51
    spinner
    0.51
    ="#
    0.51
    ква
    0.51
    Spinner
    0.51
    omani
    0.51
    POSITIVE LOGITS
     Prepare
    0.71
     Backup
    0.67
     Initialize
    0.66
    Prepare
    0.63
     Substances
    0.63
     Establishing
    0.61
     初始化
    0.61
    স্থাপন
    0.59
     ល
    0.59
    ,:)
    0.59
    Activations Density 0.000%

    No Known Activations