© 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. 117416
    Prev
    Next
    INDEX
    Explanations

    protocol buffers

    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
     Salv
    -0.82
    jest
    -0.77
    מור
    -0.76
     桶
    -0.75
     Ryzen
    -0.75
    emm
    -0.74
     cascade
    -0.74
    tector
    -0.71
    ácti
    -0.71
     škol
    -0.70
    POSITIVE LOGITS
     proto
    1.81
     Proto
    1.62
    proto
    1.56
    Proto
    1.47
    PROTO
    1.39
    protobuf
    1.33
    protoc
    1.31
     IDL
    1.28
     protobuf
    1.28
     Generated
    1.24
    Activations Density 0.075%

    No Known Activations