© 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. 11989
    Prev
    Next
    INDEX
    Explanations

    no followed by description

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

    The neuron fires most strongly on relatively rare or uncommon tokens.

    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
     Stelle
    0.43
     Tomasz
    0.43
     Leonid
    0.42
     beri
    0.42
     Svet
    0.41
     वोल्ट
    0.41
    ྵ
    0.41
    ঵
    0.41
     الماء
    0.41
     Cag
    0.40
    POSITIVE LOGITS
     inflict
    0.49
    nable
    0.49
     ofthe
    0.48
    /
    0.47
    #
    0.46
    y
    0.46
    tiempo
    0.44
     oversee
    0.43
    sof
    0.42
    ה
    0.41
    Activations Density 0.003%

    No Known Activations