© 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. 9544
    Prev
    Next
    INDEX
    Explanations

    "Cogito, ergo sum" and philosophical quotes

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

    The neuron is strongly activated by words that occur right at the start of a new sentence (the first content word following a sentence boundary).

    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
    nington
    0.64
     compliments
    0.60
     quartet
    0.60
     tailor
    0.58
     cricketer
    0.56
     motorsport
    0.56
     ties
    0.55
    ']+
    0.55
     plano
    0.54
     golfer
    0.54
    POSITIVE LOGITS
     sabiduría
    0.63
     SPEAKER
    0.62
     философ
    0.62
     diskusi
    0.61
     충분
    0.60
     BIT
    0.59
    แก้
    0.58
    瞋
    0.58
     જન્મ
    0.57
    带着
    0.56
    Activations Density 0.000%

    No Known Activations