© 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. 22-GEMMASCOPE-RES-131K
    7. 75178
    Prev
    Next
    INDEX
    Explanations

    loss or destruction

    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
     eſſ
    -1.15
     ترجمه
    -1.03
     shui
    -0.97
     hva
    -0.97
     engels
    -0.96
    lag
    -0.96
    鈥
    -0.96
    ׳
    -0.96
    
    -0.95
    ’’
    -0.94
    POSITIVE LOGITS
     during
    1.92
     by
    1.70
     from
    1.66
     earlier
    1.46
     due
    1.46
     recently
    1.32
     or
    1.27
     previous
    1.26
     in
    1.23
     recent
    1.22
    Activations Density 0.036%

    No Known Activations