© 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. 31-GEMMASCOPE-2-RES-16K
    7. 237
    Prev
    Next
    INDEX
    Explanations

    creators prioritized, lineages would

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

    This neuron spots mentions of groups or collectives of people (e.g., “students,” “participants,” “cheerleaders,” “residents”).

    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_31_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
     umožňuje
    0.31
     riguarda
    0.30
     ол
    0.30
     CONSEQUENTIAL
    0.29
     "_
    0.29
     <:
    0.29
     ":
    0.28
    ۢ
    0.28
     orice
    0.28
    Containing
    0.28
    POSITIVE LOGITS
     were
    0.91
     have
    0.80
     weren
    0.79
     estavam
    0.78
     hadden
    0.75
     بودند
    0.75
     hebben
    0.75
     avevano
    0.74
     estaban
    0.73
     knew
    0.73
    Activations Density 0.925%

    No Known Activations