© 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. 11071
    Prev
    Next
    INDEX
    Explanations

    **code, math, or data descriptions**

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

    This neuron activates on numeric tokens representing floating‐point numbers (digits with decimal points).

    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
    ﺭ
    1.02
    ר
    0.95
    reys
    0.89
    炆
    0.89
    y
    0.87
    cı
    0.86
     disregard
    0.82
     authorizes
    0.81
    bar
    0.80
     ETC
    0.80
    POSITIVE LOGITS
    いく
    0.84
    的一些
    0.80
    搾
    0.76
     disparu
    0.75
     überhaupt
    0.74
     aktiviert
    0.71
    比如說
    0.71
    \(
    0.69
    の中で
    0.68
     wundersch
    0.68
    Activations Density 0.003%

    No Known Activations