© 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. 13108
    Prev
    Next
    INDEX
    Explanations

    complex numbers

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

    The neuron consistently fires on biological and genetic terminology—e.g. species names, virus strains, gene‐recombination terms, and related taxonomy words.

    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
    ourcing
    0.74
    ண்கள்
    0.68
    eliers
    0.68
     proactively
    0.67
    КУ
    0.66
    v
    0.66
    ਰੀ
    0.65
    ěř
    0.65
    ostęp
    0.64
    廣場
    0.64
    POSITIVE LOGITS
     híbr
    1.05
     bisschen
    1.04
     hybr
    1.00
     mistura
    0.94
     evolucion
    0.93
     genes
    0.93
     ancest
    0.92
     mutated
    0.91
     эволю
    0.89
     genetic
    0.87
    Activations Density 0.044%

    No Known Activations