© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5618
    Prev
    Next
    INDEX
    Explanations

    at a rate/quantity

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

    This neuron fires on floating‐point numbers (i.e. numeric tokens containing a decimal point with three trailing digits).

    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
     увеличить
    0.63
     $,
    0.62
     увеличения
    0.61
     majest
    0.61
     збіль
    0.60
     cyclohex
    0.59
     увели
    0.59
    |$,
    0.59
     возбу
    0.57
     motionless
    0.57
    POSITIVE LOGITS
     admittedly
    0.61
     வைத்திய
    0.61
     Hussain
    0.58
     Javed
    0.56
    房
    0.55
     这个
    0.54
     Amazing
    0.54
    역시
    0.54
     साबित
    0.53
     풀
    0.53
    Activations Density 0.001%

    No Known Activations