© 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. 64129
    Prev
    Next
    INDEX
    Explanations

    protobuf related terms

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

    This neuron detects programming‐language code tokens and syntax elements (like identifiers, keywords, and punctuation) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     hap
    -0.78
     evalu
    -0.77
     Bonds
    -0.74
     Evaluation
    -0.73
    exa
    -0.72
    lismo
    -0.71
     ugyan
    -0.71
     eval
    -0.70
    yty
    -0.69
    EVAL
    -0.69
    POSITIVE LOGITS
     proto
    1.12
    Proto
    1.03
     PROTO
    1.00
    proto
    0.99
     Proto
    0.93
     attr
    0.88
    raph
    0.81
     Attr
    0.79
     protobuf
    0.79
    pb
    0.77
    Activations Density 0.010%

    No Known Activations