© 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. 5896
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

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

    The neuron strongly activates on isolated single‐character subword tokens (i.e. individual letters).

    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
    樀
    0.82
     bilayers
    0.79
     ρο
    0.77
     memorials
    0.77
     sebum
    0.73
     renormalization
    0.73
     Tübingen
    0.73
     utensil
    0.73
    奀
    0.73
     necesitamos
    0.72
    POSITIVE LOGITS
    {
    0.82
    ح
    0.75
    hot
    0.74
    tune
    0.74
    survey
    0.71
    LON
    0.71
    crown
    0.69
    extension
    0.68
    st
    0.68
    tuned
    0.68
    Activations Density 0.007%

    No Known Activations