© 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. 31-GEMMASCOPE-2-RES-16K
    4. 8287
    Prev
    Next
    INDEX
    Explanations

    .com, .org, .net domains

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

    The neuron strongly activates on standalone numeric tokens (dates, version or citation numbers) and all-caps/acronymic strings (e.g. email domains, DOIs, government or product codes).

    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_31_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
     Archim
    0.52
    藝
    0.51
     Fruits
    0.50
     Synd
    0.50
     Alf
    0.49
     lexic
    0.48
     Geophys
    0.47
     بالط
    0.46
    စ္
    0.46
     Regul
    0.46
    POSITIVE LOGITS
    .${
    0.72
    ./
    0.62
    $/,
    0.62
    ._
    0.60
    .:
    0.60
    ⣶
    0.60
    контро
    0.59
    .//
    0.59
    .$
    0.58
    .);
    0.58
    Activations Density 0.120%

    No Known Activations