© 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. 16303
    Prev
    Next
    INDEX
    Explanations

    also, or, additionally, and

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

    The neuron is specialized to pick out numeric tokens (in particular 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
     которая
    0.72
     която
    0.65
     ktorá
    0.64
     гэта
    0.64
     бесплат
    0.62
     byen
    0.62
     这
    0.62
    这将
    0.62
    这家
    0.61
     khiến
    0.61
    POSITIVE LOGITS
     hinsichtlich
    0.69
     includes
    0.61
     همچنین
    0.61
     Also
    0.59
    ALSO
    0.58
     additionally
    0.58
     También
    0.57
    includes
    0.56
    াপাশি
    0.56
     inoltre
    0.56
    Activations Density 0.513%

    No Known Activations