© 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. 11155
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formatting

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

    This neuron activates on unusual non-ASCII or multi-byte punctuation/characters (e.g. stray Unicode symbols and accent­ed bytes).

    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
     Nucleaires
    0.44
     层
    0.38
     細胞
    0.37
     SupCt
    0.37
    नाल्ड
    0.36
    etzte
    0.36
     appelle
    0.36
     冖
    0.35
     investigates
    0.35
    liche
    0.35
    POSITIVE LOGITS
     birdies
    0.34
    合わせて
    0.32
    摘
    0.32
     vời
    0.31
     staffs
    0.29
    snd
    0.29
    கூ
    0.29
    addNew
    0.29
    CopyTo
    0.29
     gimm
    0.28
    Activations Density 0.054%

    No Known Activations