© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9930
    Prev
    Next
    INDEX
    Explanations

    template to

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

    This neuron detects mentions of document templates and formatting guidelines (e.g. templates, letters, proper format).

    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
    clientHeight
    0.57
     obsc
    0.56
    synchron
    0.55
    RSSI
    0.54
    만원
    0.53
    obsc
    0.53
     apasion
    0.53
    룽
    0.52
    📵
    0.52
    ouville
    0.51
    POSITIVE LOGITS
     templates
    3.02
     template
    2.94
    模板
    2.83
    template
    2.70
     Templates
    2.69
    テンプレート
    2.67
     Template
    2.66
     шаблон
    2.52
     шабло
    2.50
    Templates
    2.44
    Activations Density 0.485%

    No Known Activations