© 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. 62607
    Prev
    Next
    INDEX
    Explanations

    programming code and concepts

    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
    Negative Logits
    intur
    -0.93
    clairage
    -0.87
     heli
    -0.82
    imler
    -0.82
     Prozess
    -0.81
     утро
    -0.80
     Myco
    -0.78
    fL
    -0.78
    Joueur
    -0.77
     Finlande
    -0.77
    POSITIVE LOGITS
     into
    1.42
    into
    1.03
     take
    0.94
    try
    0.91
     with
    0.90
     as
    0.88
     loves
    0.84
     try
    0.83
    ok
    0.81
     cốt
    0.81
    Activations Density 0.003%

    No Known Activations