© 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. 6317
    Prev
    Next
    INDEX
    Explanations

    Quicksort or sorting algorithms

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

    The neuron strongly responds to numeric tokens—especially floating‐point numbers (i.e. sequences containing a decimal point).

    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
     ഉറ
    0.69
    데
    0.67
    httparty
    0.66
    मंद
    0.65
     disseminating
    0.65
    နေရာ
    0.65
    Millis
    0.64
    itorios
    0.64
     للس
    0.61
     conserving
    0.61
    POSITIVE LOGITS
     Здесь
    0.70
    ys
    0.68
     εδώ
    0.66
    yce
    0.66
    א
    0.64
    ین
    0.64
    usz
    0.64
    anym
    0.63
     Here
    0.61
     We
    0.61
    Activations Density 0.009%

    No Known Activations