© 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. 22-GEMMASCOPE-RES-131K
    7. 24969
    Prev
    Next
    INDEX
    Explanations

    taking action and transforming

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     because
    -1.02
     páns
    -0.95
     食事
    -0.94
    værk
    -0.93
     király
    -0.92
    ↀ
    -0.92
    dott
    -0.91
    řízení
    -0.89
    savevideo
    -0.89
     this
    -0.87
    POSITIVE LOGITS
     into
    1.41
     from
    1.20
     แล้ว
    1.17
     lalu
    1.04
    แล้ว
    0.99
    ceans
    0.96
    把它
    0.94
    ouple
    0.90
    takkan
    0.88
    THON
    0.87
    Activations Density 0.050%

    No Known Activations