© 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. 10937
    Prev
    Next
    INDEX
    Explanations

    pygame.display

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

    The neuron responds strongly to discourse-marking adverbs and temporal connectives (e.g. “preceding,” “previously,” “even,” “course,” “days”), i.e. words that signal sequence or reference to earlier text or time.

    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
    дня
    0.74
    вале
    0.71
    ö
    0.71
    T
    0.70
    рити
    0.69
    חש
    0.68
    L
    0.68
    LAT
    0.68
    драт
    0.68
    বিশিষ্ট
    0.66
    POSITIVE LOGITS
    0.87
     prévenir
    0.84
    তখন
    0.80
     Advertise
    0.79
     Duque
    0.79
     informée
    0.77
     aqueles
    0.77
     aprire
    0.77
     soluções
    0.76
     ciência
    0.76
    Activations Density 0.000%

    No Known Activations