© 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. 8443
    Prev
    Next
    INDEX
    Explanations

    foreign words and numbers

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

    The neuron fires on numeric tokens—especially floating-point/statistical figures (e.g. decimals in percentages or vote‐count statistics).

    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
    .
    0.54
    1
    0.53
    2
    0.51
    i
    0.49
    ;
    0.49
    l
    0.49
    d
    0.46
    and
    0.46
    )
    0.44
     going
    0.44
    POSITIVE LOGITS
     résist
    0.50
     plupart
    0.48
    кансер
    0.45
     কীটপত
    0.45
    物質
    0.45
    ERRE
    0.45
     preoccup
    0.45
     odpor
    0.44
    faulse
    0.44
    ইস
    0.44
    Activations Density 0.090%

    No Known Activations