© 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. 16094
    Prev
    Next
    INDEX
    Explanations

    outline steps

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

    This neuron fires on tokens that appear in formal reference or citation contexts (e.g. verse numbers, journal article metadata, volume/page numbers, author or work names).

    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
    s
    0.96
    S
    0.96
    U
    0.91
    ς
    0.87
    T
    0.84
    C
    0.84
    J
    0.84
    P
    0.83
    V
    0.83
     было
    0.79
    POSITIVE LOGITS
     înc
    0.89
     compren
    0.85
     argento
    0.84
     ignor
    0.83
     attentes
    0.81
     সেনাবাহ
    0.80
    ≣
    0.79
    ূহ
    0.78
    री
    0.78
     ambienti
    0.78
    Activations Density 0.001%

    No Known Activations