© 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. 59303
    Prev
    Next
    INDEX
    Explanations

    particularly unusual moderation

    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
     varier
    -1.73
     plafon
    -1.66
    often
    -1.57
     puh
    -1.54
    满脸
    -1.52
     corect
    -1.50
    
    -1.47
     pernic
    -1.46
     zorro
    -1.45
     pegat
    -1.42
    POSITIVE LOGITS
     particularly
    3.13
     besonders
    2.66
     Particularly
    2.36
     especially
    2.34
     or
    2.33
     unusually
    2.19
     особенно
    2.16
     particularmente
    2.02
     szczególnie
    2.00
     any
    1.98
    Activations Density 0.053%

    No Known Activations