© 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. 31-GEMMASCOPE-2-RES-16K
    4. 8280
    Prev
    Next
    INDEX
    Explanations

    describing or explaining concepts

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

    This neuron is triggered by named entities—proper names and titles such as product names, event or place names, and other capitalized identifiers.

    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_31_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
     Tensorflow
    0.41
     Ook
    0.38
     Lukaku
    0.37
     Ohm
    0.36
    礡
    0.35
     Timberlake
    0.35
     Schumer
    0.35
     Kwan
    0.34
     Merkel
    0.34
     Steele
    0.34
    POSITIVE LOGITS
    fl
    0.39
    [...]
    0.35
    Но
    0.34
    
    0.34
    С
    0.33
    
    0.33
    
    0.33
    <0xF0>
    0.33
    А
    0.33
     […]
    0.32
    Activations Density 5.886%

    No Known Activations