© 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. 34-GEMMASCOPE-RES-131K
    7. 3621
    Prev
    Next
    INDEX
    Explanations

    UI label text getter/setter

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     Button
    -0.86
    keys
    -0.84
     btn
    -0.83
    action
    -0.81
     action
    -0.80
    els
    -0.80
     keys
    -0.77
    thm
    -0.77
     Sheen
    -0.76
     Keys
    -0.75
    POSITIVE LOGITS
    setText
    1.16
     setText
    1.06
    AutoSize
    1.01
     getText
    0.96
     foreground
    0.95
     text
    0.89
    Lbl
    0.84
     傳
    0.83
    foreground
    0.81
    jLabel
    0.80
    Activations Density 0.002%

    No Known Activations