© 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. 6185
    Prev
    Next
    INDEX
    Explanations

    code snippets or structured definitions

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

    The neuron strongly activates on the "ing" suffix—i.e. it picks out tokens ending in “ing.”

    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
    is
    0.87
    it
    0.84
    ری
    0.83
    ಿ
    0.79
    র
    0.79
    in
    0.77
    не
    0.77
    ir
    0.76
    al
    0.75
    িক
    0.74
    POSITIVE LOGITS
     één
    0.87
     diseñada
    0.82
     genieten
    0.82
    නයේ
    0.80
     jedno
    0.80
    ಾರ್
    0.79
    ón
    0.79
     вашего
    0.78
     perdón
    0.77
     además
    0.77
    Activations Density 0.000%

    No Known Activations