© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 16234
    Prev
    Next
    INDEX
    Explanations

    future shaped, generated using, equipped with, desires your

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

    The neuron reliably spikes on the first “content” word of each new text chunk—i.e. it marks the start of a fresh paragraph or document 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_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
     удоб
    0.75
    <0x80>
    0.71
    `).
    0.67
     יי
    0.67
     valign
    0.67
     />
    0.66
    (){
    0.65
    ↵↵↵
    0.64
     */
    0.64
     idx
    0.64
    POSITIVE LOGITS
     Journ
    0.89
     financeira
    0.81
     quinze
    0.80
     دیکھتے
    0.78
     kız
    0.76
     approu
    0.76
     empresarial
    0.76
     financiera
    0.76
     kilomètres
    0.75
     mecánico
    0.75
    Activations Density 0.000%

    No Known Activations