© 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. 68468
    Prev
    Next
    INDEX
    Explanations

    President followed by name

    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
    Not in Any Lists

    No Comments

    Negative Logits
     мои
    -1.39
     from
    -1.30
    Œuvres
    -1.28
     نباید
    -1.25
     kadang
    -1.23
    ves
    -1.21
     мою
    -1.21
    ранее
    -1.20
     пише
    -1.20
     sebaik
    -1.18
    POSITIVE LOGITS
     联
    1.38
    ないので
    1.33
    ynchronous
    1.30
    糴
    1.30
    opropyl
    1.26
    populated
    1.24
    </td>
    1.23
     further
    1.23
    ardonnay
    1.23
     Prevention
    1.22
    Activations Density 0.037%

    No Known Activations