© 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. 68483
    Prev
    Next
    INDEX
    Explanations

    xy coordinates and dimensions

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

    This neuron detects mentions of chart axes—especially references to the y-axis label and its measured width or offset.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    mathrm
    -1.75
    ！】
    -1.66
     culoare
    -1.59
     队
    -1.55
     was
    -1.42
     キャプ
    -1.41
     состоит
    -1.39
    ſelves
    -1.38
     имел
    -1.37
    でしたが
    -1.34
    POSITIVE LOGITS
    </h3>
    1.53
    ens
    1.51
    colgante
    1.48
    Править
    1.47
    аа
    1.44
    
    1.43
    𓆟
    1.42
    me
    1.41
     {
    1.40
    ᯅ
    1.38
    Activations Density 0.010%

    No Known Activations