© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13527
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by descriptive phrase

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

    This neuron strongly activates on subword tokens that include punctuation marks (e.g. hyphens or apostrophes).

    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
    或者是
    0.82
    不管是
    0.77
    <s>
    0.77
     although
    0.73
    three
    0.73
    非常的
    0.68
    但是
    0.68
    ​​​​
    0.68
     doesn
    0.67
    although
    0.67
    POSITIVE LOGITS
     `:`,
    0.77
     infos
    0.76
     coeffs
    0.75
     artworks
    0.71
     filenames
    0.71
     pptn
    0.71
     dgn
    0.71
     اہلِ
    0.69
     "(
    0.68
     meditative
    0.68
    Activations Density 0.340%

    No Known Activations