© 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. 5596
    Prev
    Next
    INDEX
    Explanations

    profit;

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

    The neuron is strongly activated by numerical tokens (e.g. digits, numeric sequences, floating‐point 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
    ynı
    0.94
     FXMLLoader
    0.86
    ᱴ
    0.86
    hentication
    0.86
    jacobian
    0.84
    ﮯ
    0.84
    ivasena
    0.83
    ยาน
    0.83
    డియో
    0.82
    ივ
    0.82
    POSITIVE LOGITS
    Headline
    0.78
    Title
    0.73
    Heading
    0.71
    Lunar
    0.69
    ש
    0.68
     ‘’
    0.68
    ंकज
    0.68
    ゝ
    0.67
     ’
    0.66
     ’’
    0.65
    Activations Density 0.001%

    No Known Activations