© 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. 8403
    Prev
    Next
    INDEX
    Explanations

    Score or Your Score

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

    The neuron strongly activates on unusually long or rare content words—i.e. long, low-frequency 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
     Barnard
    0.79
     adjudged
    0.77
     Ordn
    0.77
     Armour
    0.76
     Ashby
    0.75
     ADR
    0.72
    \_
    0.72
    ।’’
    0.70
     Complaint
    0.69
     License
    0.69
    POSITIVE LOGITS
    ambah
    0.93
    punten
    0.88
    jub
    0.86
    ﺱ
    0.84
    elekt
    0.83
    wordpress
    0.82
    baidu
    0.81
    alla
    0.79
     ignoreString
    0.79
     정보를
    0.79
    Activations Density 0.001%

    No Known Activations