© 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. 34-GEMMASCOPE-RES-131K
    7. 62688
    Prev
    Next
    INDEX
    Explanations

    Marie phoned

    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_34/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
    Related
    -0.84
    зовать
    -0.75
     Related
    -0.75
    seurs
    -0.73
    DETAILS
    -0.73
     souligne
    -0.71
     LCCN
    -0.71
     kaynağından
    -0.70
    าร์
    -0.70
     LAST
    -0.69
    POSITIVE LOGITS
     this
    1.16
     whose
    0.79
     lacer
    0.75
    Ком
    0.75
    ader
    0.75
     tässä
    0.75
     umge
    0.74
    絃
    0.72
    렵
    0.71
     Presents
    0.71
    Activations Density 0.003%

    No Known Activations