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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75098
    Prev
    Next
    INDEX
    Explanations

    summarizing or concluding thought

    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
     hacerlo
    -1.27
     respectivos
    -1.12
     obie
    -1.03
    ਛ
    -0.94
     उनकी
    -0.94
     
    -0.93
    っております
    -0.93
     WaitForSeconds
    -0.93
    gehende
    -0.93
    specially
    -0.93
    POSITIVE LOGITS
    Conclusion
    1.19
     dunque
    1.13
    इन
    1.09
     lastly
    1.08
    Lastly
    1.08
    以上
    1.06
     Ultimately
    1.05
     conclusion
    1.05
    Ultimately
    1.05
     Lastly
    1.02
    Activations Density 0.005%

    No Known Activations