© 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. 68694
    Prev
    Next
    INDEX
    Explanations

    slugs and slag

    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
     But
    -2.83
    ƾ
    -2.59
    訁
    -2.50
     verdadero
    -2.47
    ⁛
    -2.39
    真的很
    -2.38
    //{
    -2.30
     you
    -2.30
     européens
    -2.30
    凊
    -2.28
    POSITIVE LOGITS
     &&
    2.59
    '
    2.44
    𓋼
    2.39
    戕
    2.27
     участия
    2.11
    ൎ
    2.06
    鶚
    2.05
    除此
    1.96
    ⃚
    1.94
    更容易
    1.91
    Activations Density 0.002%

    No Known Activations