© 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. 10467
    Prev
    Next
    INDEX
    Explanations

    starting explaining something

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

    The neuron fires on sentence-initial discourse markers—words like “So,” “And,” “Now,” “We,” “Okay,” or “You” that kick off new tutorial/instruction steps.

    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
     Վ
    0.75
     الله
    0.72
     Vào
    0.71
     土
    0.70
     SKIN
    0.70
     其他
    0.68
     Всем
    0.68
     Nationality
    0.68
     把
    0.67
     COMMISSION
    0.67
    POSITIVE LOGITS
     this
    0.67
     ditulis
    0.61
    ഹന
    0.60
     kirjo
    0.60
     gekennzeichnet
    0.60
    писание
    0.56
     vekt
    0.56
     escrib
    0.56
     biocompat
    0.56
     graduate
    0.55
    Activations Density 0.004%

    No Known Activations