© 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. 30124
    Prev
    Next
    INDEX
    Explanations

    questions and code comments

    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
    Ə
    -0.72
     lysis
    -0.72
     conservé
    -0.70
     λεπ
    -0.70
     étrangères
    -0.69
     kleuren
    -0.69
    ómetros
    -0.69
    Ը
    -0.68
     régionales
    -0.66
    ängen
    -0.66
    POSITIVE LOGITS
     baseline
    2.55
    baseline
    2.28
     Baseline
    2.11
    Baseline
    2.08
    BASELINE
    1.53
     asc
    1.38
     basement
    1.23
     desc
    1.16
     base
    1.16
    asc
    1.15
    Activations Density 0.039%

    No Known Activations