© 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. 5738
    Prev
    Next
    INDEX
    Explanations

    Okay, let's break down

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

    The neuron is tuned to detect numeric tokens and numerical data—e.g. numbers, dates, measurements, or statistical figures.

    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
     Beech
    0.60
    ஊ
    0.57
     वृत्त
    0.57
     ஊ
    0.55
     horseshoe
    0.55
     Peck
    0.55
     menyel
    0.54
    ylmethylsulfanyl
    0.54
     მიმო
    0.54
     Streets
    0.53
    POSITIVE LOGITS
    IQUE
    0.59
    Template
    0.56
    TeV
    0.56
    ique
    0.56
    Port
    0.55
    Comb
    0.55
    Pers
    0.55
    =${
    0.54
    ${
    0.52
    Over
    0.52
    Activations Density 0.068%

    No Known Activations