© 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. 10-GEMMASCOPE-RES-131K
    7. 58207
    Prev
    Next
    INDEX
    Explanations

    online services and documentation

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     réjou
    -1.34
     byť
    -1.31
    鮠
    -1.29
    驺
    -1.26
    EREF
    -1.20
    TokenNameEQUAL
    -1.19
    ӧ
    -1.19
    मिक
    -1.16
     amélior
    -1.16
    ediakan
    -1.15
    POSITIVE LOGITS
     could
    1.35
     доход
    1.17
     इस
    1.13
     always
    1.12
    忉
    1.11
     would
    1.10
    (^_^;)
    1.09
     circling
    1.08
    Dijo
    1.08
     So
    1.07
    Activations Density 0.027%

    No Known Activations