© 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. 10767
    Prev
    Next
    INDEX
    Explanations

    activity burning

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

    The neuron fires on numeric tokens—especially decimal‐point numbers and other standalone numerical values.

    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
    бок
    0.80
    рт
    0.79
    т
    0.76
    чу
    0.76
    ватися
    0.76
    र्च
    0.74
     allowNull
    0.73
    пера
    0.73
    ᄁ
    0.72
    тя
    0.72
    POSITIVE LOGITS
     воздух
    0.84
     outro
    0.83
     Darmstadt
    0.83
     Air
    0.80
     relacionamento
    0.79
     Cumbria
    0.78
     Blackpool
    0.77
     Clar
    0.77
     Clements
    0.77
     Braunsch
    0.77
    Activations Density 0.000%

    No Known Activations