© 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. 11213
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

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

    The neuron fires on uppercase abbreviations and acronyms (e.g. “CI,” “RR,” “UM,” “MB,” etc.) typically used for statistical or domain‐specific measures.

    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
     (
    0.66
     (\
    0.60
    g
    0.59
    m
    0.58
     உள்ளிட்ட
    0.57
     ("
    0.57
     for
    0.56
     (“
    0.56
     (\"
    0.56
    is
    0.55
    POSITIVE LOGITS
    兩人
    0.63
     Gente
    0.58
     chuva
    0.56
    ছাই
    0.55
    晦
    0.55
     brillante
    0.54
     ombre
    0.54
    两人
    0.53
     Cannes
    0.53
     politie
    0.53
    Activations Density 0.002%

    No Known Activations