© 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. 62637
    Prev
    Next
    INDEX
    Explanations

    async in code

    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
    푔
    -1.11
     then
    -1.10
    醪
    -1.05
    锨
    -1.05
     nā
    -1.04
     rú
    -1.03
    CURSO
    -1.03
    趼
    -1.02
    yse
    -1.01
    ⃤
    -1.00
    POSITIVE LOGITS
    r
    1.29
    Well
    1.00
     Sitzung
    0.99
    w
    0.98
    p
    0.98
    P
    0.96
    k
    0.96
    That
    0.95
    def
    0.91
    それだけ
    0.87
    Activations Density 0.001%

    No Known Activations