© 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. 101033
    Prev
    Next
    INDEX
    Explanations

    marriage of, unpacking, snapshots of, away from

    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
     représenter
    -1.37
     objectifs
    -1.30
    обы
    -1.25
    Bordeaux
    -1.24
    Govt
    -1.24
     émer
    -1.22
     véhic
    -1.21
    ኵ
    -1.20
    Irlande
    -1.20
     célè
    -1.20
    POSITIVE LOGITS
     their
    1.57
    ”,
    1.56
    ”),
    1.39
     also
    1.38
    }$,
    1.38
     within
    1.34
     then
    1.32
    。”
    1.30
    ],
    1.29
     ),
    1.29
    Activations Density 0.266%

    No Known Activations