© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 3010
    Prev
    Next
    INDEX
    Explanations

    I believe

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

    This neuron identifies the opening words of numbered or bulleted list items—that is, sentence-initial tokens in a list.

    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
     but
    0.62
    但也
    0.61
     অবশ্য
    0.57
    但
    0.57
     কিন্তু
    0.55
     aber
    0.52
    但不
    0.51
     lekin
    0.51
     auch
    0.51
     though
    0.50
    POSITIVE LOGITS
    ocalypse
    0.64
    bedaan
    0.63
    ͟
    0.62
     bukanlah
    0.61
    eseorang
    0.61
     voluntad
    0.59
    álogo
    0.59
    helloworld
    0.58
     volontà
    0.57
    ‼
    0.57
    Activations Density 1.335%

    No Known Activations