© 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. 3501
    Prev
    Next
    INDEX
    Explanations

    wand, wander, Wang, Wanz

    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
    利的
    -0.77
     valg
    -0.72
     拉
    -0.71
     enlisted
    -0.71
     contagio
    -0.70
    His
    -0.68
     لط
    -0.68
    ǁ
    -0.67
    convention
    -0.67
    日本酒
    -0.67
    POSITIVE LOGITS
    Wand
    1.00
    wand
    0.80
     Wandering
    0.79
     Wand
    0.79
    sworth
    0.75
    Nomad
    0.73
    ób
    0.73
     Wanda
    0.72
     Wander
    0.71
     ANOVA
    0.71
    Activations Density 0.011%

    No Known Activations