© 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. 16042
    Prev
    Next
    INDEX
    Explanations

    statuses, breaks, and Russian fatigue

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

    The neuron activates whenever it encounters a floating‐point number (a numeric token 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
    p
    0.77
    k
    0.74
    ri
    0.72
    x
    0.71
    kach
    0.69
    c
    0.68
     Amaya
    0.65
     varn
    0.64
    .}
    0.64
    certs
    0.63
    POSITIVE LOGITS
     Республики
    0.96
    𒄿
    0.91
     Помимо
    0.89
     бывшего
    0.82
     Такие
    0.80
     Observ
    0.80
    傊
    0.79
    Virtual
    0.79
     виртуа
    0.79
     দ্যা
    0.79
    Activations Density 0.000%

    No Known Activations