© 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. 5355
    Prev
    Next
    INDEX
    Explanations

    focus on

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

    The neuron strongly activates on words that signal data‐oriented report sections or quantitative content—terms like “statistics,” “overview,” “information,” “basic,” or “analysis.”

    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
     Она
    0.84
     Её
    0.84
     przek
    0.82
    <start_of_image>
    0.82
     Такая
    0.79
     devolución
    0.79
    ו
    0.79
    or
    0.77
    тной
    0.77
     incênd
    0.77
    POSITIVE LOGITS
    ავლ
    0.77
    \%$
    0.75
    各
    0.71
    ْب
    0.70
    地区的
    0.70
    ണ്ഡി
    0.70
    ْس
    0.70
    %、
    0.69
     opinion
    0.68
    بیل
    0.68
    Activations Density 0.001%

    No Known Activations