© 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. 11031
    Prev
    Next
    INDEX
    Explanations

    stylistic elements and historical periods

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

    The neuron activates strongly on numeric identifiers and labels (e.g. example numbers, component or figure reference numbers) 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
    не
    0.85
     antigos
    0.83
    𝐝
    0.79
    翮
    0.77
    ̣c
    0.75
     Catawiki
    0.75
     desserts
    0.75
     couplers
    0.75
     soups
    0.74
    𝚖
    0.73
    POSITIVE LOGITS
     Bunun
    0.76
     grun
    0.71
    ayaran
    0.70
    いや
    0.70
    斓
    0.69
    Preparation
    0.64
    긁
    0.63
     Adapun
    0.63
    Except
    0.62
    سى
    0.61
    Activations Density 0.001%

    No Known Activations