© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10243
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly activated by floating‐point numeric tokens (i.e. decimal numbers) in the text.

    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
    >
    0.88
    .
    0.86
    z
    0.86
    ী
    0.84
    ine
    0.81
    j
    0.79
    f
    0.79
    S
    0.78
    =
    0.78
    ين
    0.77
    POSITIVE LOGITS
    ವ್
    0.96
     courageous
    0.94
    プラグ
    0.92
     observatory
    0.88
     foreseeable
    0.88
    ます
    0.86
     paediatric
    0.86
     proudly
    0.85
     reflective
    0.84
     pebble
    0.84
    Activations Density 0.000%

    No Known Activations