© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13423
    Prev
    Next
    INDEX
    Explanations

    Tkinter or older Xbox

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

    The neuron is a “rarity detector” – it spikes on low‐frequency, unusual tokens (odd or uncommon words/subword pieces).

    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
    MAN
    0.80
    ்த்த
    0.80
    aras
    0.73
    اہر
    0.71
    成员
    0.70
    بر
    0.69
    imi
    0.68
    ippers
    0.68
    SH
    0.67
    MI
    0.67
    POSITIVE LOGITS
     канализа
    0.85
     कारखाना
    0.85
    স্বরূপ
    0.83
    ו
    0.83
     Dạ
    0.81
    Appuntamento
    0.81
    interpolate
    0.78
     Ты
    0.77
     MANUFACTURING
    0.77
     Марина
    0.76
    Activations Density 0.000%

    No Known Activations