© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2601
    Prev
    Next
    INDEX
    Explanations

    law and code designations

    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
    scan
    -0.73
     rato
    -0.72
     Tom
    -0.69
     Aussehen
    -0.67
    strip
    -0.67
    Comparing
    -0.67
    zone
    -0.66
    Gründe
    -0.65
    how
    -0.65
     насколько
    -0.65
    POSITIVE LOGITS
     Ordinance
    0.88
     ordinance
    0.86
    Před
    0.85
    ringar
    0.79
    chul
    0.79
     Collegiate
    0.78
     rekke
    0.78
    behaved
    0.77
     Interstate
    0.77
     Uttar
    0.77
    Activations Density 0.009%

    No Known Activations