© 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. 57972
    Prev
    Next
    INDEX
    Explanations

    comparing measured data

    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
    
    -1.87
    €“
    -1.86
    </u>
    -1.85
    ндарт
    -1.84
    ⬈
    -1.83
    ۴
    -1.81
    StoryboardSegue
    -1.80
    nalités
    -1.80
    TargetException
    -1.76
    BeginInit
    -1.75
    POSITIVE LOGITS
     that
    1.86
    '
    1.80
     because
    1.71
     this
    1.67
     there
    1.67
     various
    1.60
     numerous
    1.59
     the
    1.56
     at
    1.55
     enormous
    1.52
    Activations Density 0.029%

    No Known Activations