© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113938
    Prev
    Next
    INDEX
    Explanations

    variable names: C, CR, CF, CW

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

    Looking at the activations, this neuron strongly activates on: - "Consider" (99) - Single-letter variables in code/math contexts: "c" (232, 312, 192, 188, 164, 142, 258), "C

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -3.33
    lossians
    -2.88
    へ向
    -2.58
    
    -2.52
    逦
    -2.50
    凩
    -2.39
    桫
    -2.34
    狲
    -2.33
     Japón
    -2.33
     Alemania
    -2.31
    POSITIVE LOGITS
    0
    2.97
    ">
    2.80
    ");
    2.75
    th
    2.66
    ()
    2.50
    </b>
    2.38
    (){
    2.38
    }{
    2.36
    ){
    2.36
            
    2.30
    Activations Density 7.471%

    No Known Activations