© 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. 10273
    Prev
    Next
    INDEX
    Explanations

    lists and structure

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

    The neuron is essentially spotting low‐frequency (rare or “uncommon”) 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
     Hành
    0.59
     Органи
    0.59
    ंचित
    0.57
     Bóng
    0.56
     Cependant
    0.56
     Viên
    0.55
    䬲
    0.55
     Außerdem
    0.55
    ल्लिंग
    0.55
     Quadrupèdes
    0.55
    POSITIVE LOGITS
    .
    0.68
    -
    0.65
    :
    0.64
    /
    0.61
     /
    0.61
    ?
    0.61
     
    0.60
    ;
    0.60
    ,
    0.59
    _
    0.56
    Activations Density 0.677%

    No Known Activations