© 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. 3624
    Prev
    Next
    INDEX
    Explanations

    previous versions or generations

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

    The neuron fires on formal, domain-specific nouns used in classification or measurement contexts (e.g. “subfamily,” “species,” “period,” “average”).

    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
     أو
    0.71
     или
    0.68
     কিংবা
    0.64
     或
    0.63
    Então
    0.63
     বা
    0.62
    场地
    0.61
    prise
    0.59
    mensaje
    0.59
    mensagem
    0.59
    POSITIVE LOGITS
     between
    0.71
     genus
    0.70
     generations
    0.68
    :
    0.67
     homologs
    0.67
     Between
    0.66
     hierarchical
    0.66
     eukaryotes
    0.65
     entities
    0.64
     Dept
    0.64
    Activations Density 0.003%

    No Known Activations