© 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. 50064
    Prev
    Next
    INDEX
    Explanations

    special characters and code delimiters

    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
     or
    -1.60
     from
    -1.54
     more
    -1.33
     all
    -1.33
     in
    -1.31
     will
    -1.27
     should
    -1.24
     so
    -1.22
    Even
    -1.20
    Also
    -1.18
    POSITIVE LOGITS
     crappy
    1.24
    摟
    1.21
     Dinas
    1.20
    
    1.17
    ,;
    1.17
    owing
    1.15
     vorgesehen
    1.10
     debacle
    1.09
     bevorzug
    1.08
    說道
    1.08
    Activations Density 0.004%

    No Known Activations