© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9388
    Prev
    Next
    INDEX
    Explanations

    needs, last, when

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

    This neuron strongly activates on the first substantive content word that begins a new paragraph 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_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
     собственных
    0.71
    te
    0.70
    it
    0.70
    
    0.67
     toured
    0.66
    nds
    0.66
     Airplane
    0.66
    🙏🏻
    0.66
    nt
    0.66
     Autres
    0.65
    POSITIVE LOGITS
     radiolysis
    0.76
    放射
    0.75
    ਖ਼
    0.74
     rectMode
    0.73
    㽞
    0.71
     surfact
    0.71
    にお
    0.68
     ویڈیو
    0.68
    उदा
    0.68
    сний
    0.68
    Activations Density 0.000%

    No Known Activations