© 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. 22485
    Prev
    Next
    INDEX
    Explanations

    verbal pauses and fillers

    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
     multifaceted
    -1.88
     L
    -1.78
     countless
    -1.76
     using
    -1.75
     exquisitely
    -1.73
     Some
    -1.71
     all
    -1.71
     burgeoning
    -1.70
     B
    -1.68
     innumerable
    -1.66
    POSITIVE LOGITS
    during
    2.09
    鉭
    1.89
    ੲ
    1.87
     ity
    1.84
    wonderful
    1.80
     Dinas
    1.75
    €“
    1.75
    ᴎ
    1.73
     oscuro
    1.71
    鼉
    1.71
    Activations Density 0.001%

    No Known Activations