© 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. 38504
    Prev
    Next
    INDEX
    Explanations

    url protocol separators

    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
    ⚋
    -2.52
    呖
    -2.25
    または
    -2.16
    кий
    -2.09
     новая
    -2.08
    も
    -2.08
    ௮
    -2.06
     就
    -2.05
     '-
    -2.02
     "'
    -1.98
    POSITIVE LOGITS
    ”
    2.72
    e
    2.38
    ://
    2.31
    {
    2.23
    ’?
    2.20
    精华
    2.14
    ar
    2.06
    来自于
    2.05
    a
    2.03
    
    1.99
    Activations Density 0.059%

    No Known Activations