© 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. 6738
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens containing decimal points—that is, floating-point numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the letter "E" when it appears as a standalone character or abbreviation in technical, formal, or structured text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    abbreviations and capitalized proper-noun fragments, such as initials, directional abbreviations, and formal citation elements within lists or headings.

    oai_token-act-pair · gpt-5Triggered 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
    Mvc
    0.77
    َان
    0.76
    ebabkan
    0.75
    ucristo
    0.75
     نکن
    0.74
    usstsein
    0.74
    entlich
    0.71
    waan
    0.71
    慚
    0.71
    ステル
    0.70
    POSITIVE LOGITS
    Р
    0.78
     மற்றும்
    0.77
     가지
    0.77
     ਅਤੇ
    0.77
     comulti
    0.75
    প্রতি
    0.74
     clockwise
    0.74
     and
    0.73
     각
    0.73
    А
    0.73
    Activations Density 0.002%

    No Known Activations