© 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. 11891
    Prev
    Next
    INDEX
    Explanations

    text formatting and code structure

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

    The neuron strongly activates on mentions of quantitative metrics or statistical measures (e.g., indices, reading levels, numeric data descriptors).

    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
    <unused2157>
    0.38
     o
    0.34
     Fior
    0.32
    <unused2200>
    0.32
    下列
    0.32
     Ezek
    0.32
     Oats
    0.32
    <unused2187>
    0.32
     Suppose
    0.32
     Illuminate
    0.32
    POSITIVE LOGITS
    лё
    0.39
    kový
    0.38
    г
    0.38
    uky
    0.38
    idlo
    0.38
    uene
    0.37
    ijl
    0.37
    vertrag
    0.37
    ѧ
    0.37
    д
    0.36
    Activations Density 2.835%

    No Known Activations