© 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. 114184
    Prev
    Next
    INDEX
    Explanations

    `blur`, `change`, `load`, `wrinkled`, `heart`

    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
     billeder
    -1.38
     ulike
    -1.38
     forskjellige
    -1.30
     medarbe
    -1.30
    metery
    -1.30
     løpet
    -1.29
    孰
    -1.28
     forbindelse
    -1.27
     nueva
    -1.27
    these
    -1.25
    POSITIVE LOGITS
     who
    1.45
    اعم
    1.27
     einzige
    1.23
    　・
    1.19
    atação
    1.16
     elég
    1.13
     pharmacie
    1.13
    蜂蜜
    1.13
    パパ
    1.12
     ratific
    1.12
    Activations Density 0.002%

    No Known Activations