© 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. 11913
    Prev
    Next
    INDEX
    Explanations

    Gemma an AI assistant

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

    The neuron strongly activates on uncommon content words (nouns or adjectives) rather than on common function words.

    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
    *
    0.82
    *((*
    0.79
     случа
    0.73
     Brunch
    0.73
     numerosi
    0.72
    >)`](
    0.71
    ולנדי
    0.70
     Bungal
    0.70
    branchNode
    0.70
    。
    0.70
    POSITIVE LOGITS
    س
    0.88
     কাহার
    0.75
     ক্রিম
    0.75
    pas
    0.74
    arı
    0.73
    串口
    0.71
    adım
    0.71
    alities
    0.70
    hadoop
    0.70
     धनराशि
    0.70
    Activations Density 0.000%

    No Known Activations