© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5196
    Prev
    Next
    INDEX
    Explanations

    digits and punctuation

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

    The neuron activates on numeric tokens—especially citation details like years, volumes, page ranges, and decimal‐formatted numbers.

    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
    𝑒
    0.13
    而后
    0.13
     الكسور
    0.13
    }:{
    0.13
    สัน
    0.13
     násled
    0.13
    )])
    0.12
    )]);
    0.12
    AL
    0.12
    }));
    0.12
    POSITIVE LOGITS
     auspices
    0.15
     speeches
    0.15
     outcry
    0.14
     »
    0.14
     bilingual
    0.14
     regulations
    0.14
     Seniors
    0.14
     Manuscripts
    0.13
     geographically
    0.13
     monologue
    0.13
    Activations Density 0.002%

    No Known Activations