© 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. 10-GEMMASCOPE-RES-131K
    7. 10029
    Prev
    Next
    INDEX
    Explanations

    gson and GSM

    np_acts-logits-general · gemini-2.5-flash-lite

    the term "Gson" (a Java JSON library).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     This
    -3.13
    潆
    -2.83
     They
    -2.77
     monti
    -2.72
     That
    -2.67
     könnten
    -2.67
     stata
    -2.66
    Ꮟ
    -2.61
     persino
    -2.59
    what
    -2.58
    POSITIVE LOGITS
     
    3.14
    2
    2.52
    the
    2.50
    水を
    2.44
     —
    2.42
    身为
    2.33
    苤
    2.33
     oito
    2.33
    .
    2.31
    {
    2.25
    Activations Density 0.002%

    No Known Activations