© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59064
    Prev
    Next
    INDEX
    Explanations

    start of content/code block

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

    This neuron fires on numeric values and their associated parameter assignments (e.g. dimensions, option keys, or node attributes) in LaTeX commands.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ɵɵelementEnd
    -0.79
    вил
    -0.77
    という言葉
    -0.77
     become
    -0.72
    maven
    -0.69
     end
    -0.69
     рассказать
    -0.68
    lauben
    -0.68
     uhd
    -0.68
     manejar
    -0.68
    POSITIVE LOGITS
     ♪
    1.02
    {$\
    1.00
    ();}
    0.96
    Rotated
    0.94
    小さく
    0.90
    );}
    0.90
    lasts
    0.89
     znam
    0.88
     boxes
    0.87
    Continued
    0.87
    Activations Density 0.010%

    No Known Activations