© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2894
    Prev
    Next
    INDEX
    Explanations

    the following is

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

    This neuron detects the common list‐introduction phrase “The following …,” especially the “The following list of” construction that kicks off enumerations.

    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
     Etat
    1.08
    る
    1.01
     Epilepsy
    1.00
     own
    0.94
     innervation
    0.94
    ي
    0.92
     αυτό
    0.88
     Epile
    0.88
     ECO
    0.87
     Vocational
    0.85
    POSITIVE LOGITS
    ти
    1.18
    是我
    1.16
    maßen
    1.13
    are
    1.05
    toare
    1.05
    س
    1.04
    の場合
    1.02
    types
    1.01
    тировать
    1.00
    dtypes
    0.98
    Activations Density 0.016%

    No Known Activations