© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12980
    Prev
    Next
    INDEX
    Explanations

    green text or function

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

    The neuron is detecting web addresses and similar domain‐style tokens (e.g. “com” and other uppercase/acronym sequences you see in URLs).

    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
     用
    0.88
     ステンレス
    0.87
     }}{\
    0.82
     Selain
    0.80
    ））
    0.80
     IBOutlet
    0.79
    ﻊ
    0.79
     沒有
    0.77
    izienz
    0.77
     quanh
    0.76
    POSITIVE LOGITS
    ची
    0.79
    UTS
    0.70
    ame
    0.68
    ς
    0.68
    Tri
    0.67
     introductions
    0.67
    base
    0.66
    ंची
    0.66
     her
    0.66
    Unis
    0.66
    Activations Density 0.000%

    No Known Activations