© 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. 22-GEMMASCOPE-RES-131K
    7. 34062
    Prev
    Next
    INDEX
    Explanations

    comparing quantities or using specific technical terms

    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_22/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
     devaient
    -0.96
     tênis
    -0.94
    Conclusiones
    -0.92
    骷
    -0.91
     rapports
    -0.91
     caráter
    -0.91
     acheter
    -0.90
     activer
    -0.89
    大満足
    -0.89
     arrivent
    -0.89
    POSITIVE LOGITS
     or
    1.59
     still
    1.58
     then
    1.27
     will
    1.01
    还是
    0.98
     gets
    0.97
    Ainda
    0.94
     Still
    0.93
    ඔ
    0.93
     subsequently
    0.90
    Activations Density 0.047%

    No Known Activations