© 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. 4535
    Prev
    Next
    INDEX
    Explanations

    variables or abbreviations

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

    The neuron strongly activates on floating-point numeric tokens (numbers 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
    𝚌
    0.83
    fueled
    0.79
     aDecoder
    0.78
    dí
    0.77
    c
    0.76
    ರ
    0.75
    cual
    0.75
     servi
    0.74
    fälle
    0.74
    𝘾
    0.74
    POSITIVE LOGITS
    ’
    0.86
    ﻄ
    0.79
    AM
    0.75
     gambar
    0.75
    0
    0.74
    襬
    0.73
     меня
    0.73
     снаб
    0.72
    ണ്ണി
    0.68
     CONNE
    0.68
    Activations Density 0.000%

    No Known Activations