© 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. 13068
    Prev
    Next
    INDEX
    Explanations

    SQL SELECT statements

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

    The neuron detects numeric tokens representing floating‐point values (numbers 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
    ed
    0.91
    ي
    0.90
    אן
    0.87
    ق
    0.86
    ف
    0.83
    Children
    0.81
     beaten
    0.79
     Auxiliary
    0.78
    י
    0.78
    یوں
    0.75
    POSITIVE LOGITS
     hayas
    0.83
     conceit
    0.82
     pudieran
    0.80
     hảo
    0.77
     andar
    0.75
     publique
    0.74
    geschichte
    0.74
    webContents
    0.74
     dicht
    0.73
     сайте
    0.73
    Activations Density 0.000%

    No Known Activations