© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82492
    Prev
    Next
    INDEX
    Explanations

    after events

    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
    trường
    -1.08
    کات
    -1.02
     spolup
    -1.02
     signe
    -1.00
    それにしても
    -0.94
    浑身
    -0.94
     spou
    -0.93
    ándose
    -0.91
    子育て
    -0.91
     respondió
    -0.90
    POSITIVE LOGITS
     completion
    2.31
     arrival
    2.02
     conclusion
    1.80
     expiration
    1.73
     end
    1.73
     publication
    1.72
     onset
    1.68
     start
    1.64
     inception
    1.59
     release
    1.50
    Activations Density 0.065%

    No Known Activations