© 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. 30209
    Prev
    Next
    INDEX
    Explanations

    Java code keywords

    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
    Not in Any Lists

    No Comments

    Negative Logits
     beber
    -1.03
    bezpiecz
    -1.01
    ТЕЛЬ
    -0.98
    tricos
    -0.96
    haviours
    -0.92
    ísima
    -0.92
     RemoteException
    -0.90
    returning
    -0.90
    дки
    -0.89
    utang
    -0.89
    POSITIVE LOGITS
    final
    1.47
     final
    1.45
    â
    0.93
    if
    0.91
     here
    0.89
    ftest
    0.88
     just
    0.85
    ac
    0.84
     FINAL
    0.83
     進
    0.82
    Activations Density 0.007%

    No Known Activations