© 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. 11060
    Prev
    Next
    INDEX
    Explanations

    foreign language characters and special symbols

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

    The neuron fires on informal, emotive or exclamatory words and phrases (e.g. “Oh,” “love,” “keeping”) that signal a conversational, emotionally charged style.

    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
    邺
    0.84
     Departing
    0.84
    ٻ
    0.83
    ຫລ
    0.82
     হুগলীর
    0.81
    вається
    0.80
    EditDialogOpen
    0.80
     علاوه
    0.80
     इम्मेडिएटली
    0.78
     કોઈ
    0.77
    POSITIVE LOGITS
    y
    1.04
    e
    0.91
    ي
    0.90
    ل
    0.86
     agora
    0.85
    א
    0.79
    י
    0.78
     mijn
    0.75
    i
    0.74
    m
    0.74
    Activations Density 0.001%

    No Known Activations