© 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. 127893
    Prev
    Next
    INDEX
    Explanations

    router and routes

    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
     or
    -1.27
     because
    -1.20
     data
    -1.12
     of
    -1.05
     by
    -1.05
     comes
    -1.03
     longstanding
    -1.02
     млрд
    -0.99
     on
    -0.98
     With
    -0.98
    POSITIVE LOGITS
    continence
    1.33
     кӀ
    1.20
    記得
    1.16
    ፱
    1.13
    cisive
    1.13
    visiting
    1.13
    ふり
    1.12
    ffo
    1.06
     Dinas
    1.05
    Asking
    1.05
    Activations Density 0.001%

    No Known Activations