© 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. 7689
    Prev
    Next
    INDEX
    Explanations

    tokens that form words or code snippets

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

    The neuron strongly activates on the special “<bos>” (begin-of-sequence) token, signaling the start of a new document or segment.

    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
     робити
    0.59
     disegnare
    0.58
     ಹು
    0.57
    做什么
    0.57
    addle
    0.55
    Doing
    0.55
     القيام
    0.54
     色
    0.53
     anglais
    0.52
    anku
    0.50
    POSITIVE LOGITS
     pyplot
    0.60
    tkinter
    0.59
    ſon
    0.57
     সেন্টার
    0.55
     Mathe
    0.55
     خار
    0.54
    肯
    0.54
    ===========
    0.54
     সোসাই
    0.54
     Centre
    0.53
    Activations Density 0.319%

    No Known Activations