© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93418
    Prev
    Next
    INDEX
    Explanations

    serialization to json

    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
     burbu
    -0.84
    囤
    -0.84
    Referințe
    -0.82
    Ery
    -0.80
     drau
    -0.80
     早餐
    -0.79
    ärke
    -0.79
     geladeira
    -0.77
     poitrine
    -0.76
    splitContainer
    -0.75
    POSITIVE LOGITS
     to
    1.58
     json
    1.49
     JSON
    1.45
    toMap
    1.36
    toArray
    1.27
    json
    1.27
     toArray
    1.25
    JSON
    1.23
    toJSON
    1.21
     serialize
    1.18
    Activations Density 0.014%

    No Known Activations