© 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. 5380
    Prev
    Next
    INDEX
    Explanations

    required, depends, integration

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

    The neuron fires on numeric tokens formatted as multi-digit decimals (i.e. floating-point numbers).

    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
     مها
    0.61
    τει
    0.59
    墮
    0.58
     nineties
    0.57
    [
    0.56
    !
    0.55
     العدد
    0.55
     ][
    0.55
    "][
    0.54
    !!"
    0.54
    POSITIVE LOGITS
    égation
    0.70
    ﹚
    0.70
    坏
    0.67
    akanan
    0.67
    MaxPooling
    0.67
    Nuestro
    0.66
    hoti
    0.64
    फार
    0.64
     reconstitution
    0.63
    rió
    0.63
    Activations Density 0.003%

    No Known Activations