© 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. 5017
    Prev
    Next
    INDEX
    Explanations

    second one

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

    The neuron strongly activates on word‐piece tokens that begin a new unit after punctuation or other boundaries (e.g. the “t” in “n’t,” pieces in hyphenated words, or tokens immediately following punctuation).

    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
    一定的
    1.05
    Ꮰ
    0.94
    ちょう
    0.90
    Ᏻ
    0.86
    дні
    0.86
    ટ્સ
    0.84
    dzić
    0.84
    ຟ
    0.84
    ţiile
    0.83
    цима
    0.82
    POSITIVE LOGITS
    ↵
    0.87
     anderer
    0.78
    I
    0.72
     I
    0.72
     ambul
    0.69
    (
    0.68
     embal
    0.67
     allgeme
    0.66
     as
    0.65
     erset
    0.65
    Activations Density 0.000%

    No Known Activations