© 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. 73611
    Prev
    Next
    INDEX
    Explanations

    numbers following 'n' or after '='

    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
     final
    -1.25
    final
    -1.17
    最後
    -1.13
    最后
    -1.04
     最終
    -1.00
     finais
    -0.96
     ostat
    -0.96
    Final
    -0.96
    最後に
    -0.91
    最終
    -0.89
    POSITIVE LOGITS
     next
    1.40
     nxt
    1.01
     nächste
    1.01
     nächsten
    0.95
    Next
    0.95
    接下来
    0.93
    next
    0.93
    Siguiente
    0.91
    paravant
    0.90
    nextNode
    0.89
    Activations Density 0.024%

    No Known Activations