© 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. 57047
    Prev
    Next
    INDEX
    Explanations

    suggest to review

    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
     Console
    -1.02
    illé
    -0.96
    ibley
    -0.91
    Signing
    -0.87
    ámos
    -0.85
    avelength
    -0.84
    държа
    -0.83
    systemctl
    -0.82
    Thick
    -0.82
     الشاشة
    -0.81
    POSITIVE LOGITS
     recommendations
    2.81
     recommend
    2.56
     recommendation
    2.47
     recommended
    2.16
     recommending
    2.06
     Recommendations
    2.03
     recommends
    1.97
     Recommend
    1.91
     advise
    1.90
    recommendations
    1.86
    Activations Density 0.032%

    No Known Activations