© 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. 14138
    Prev
    Next
    INDEX
    Explanations

    market chaos

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

    This neuron fires on infrequent or distinctive tokens (e.g. rare words, proper names, or symbols) that stand out as unusually specific in the text.

    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
    圳
    0.80
     ازيكم
    0.78
    Ｒ
    0.72
    勰
    0.72
    昅
    0.71
    dessä
    0.71
    男生
    0.70
    niejsze
    0.69
    込んだ
    0.69
    rital
    0.69
    POSITIVE LOGITS
    .
    0.89
     groaned
    0.77
    וף
    0.76
    ת
    0.74
     phe
    0.73
     צו
    0.73
    มุม
    0.71
    ("\"
    0.69
    ண்முக
    0.68
    মূলক
    0.67
    Activations Density 0.000%

    No Known Activations