© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84229
    Prev
    Next
    INDEX
    Explanations

    protobuf, dependency, status code

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

    The neuron responds to programming‐language code elements (identifiers, package/import names, dots, etc.).

    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
     just
    -1.32
     first
    -1.29
     even
    -1.20
     on
    -1.19
     during
    -1.11
     all
    -1.11
     almost
    -1.05
     their
    -1.02
     not
    -1.01
     both
    -1.01
    POSITIVE LOGITS
    protobuf
    1.40
     proto
    1.24
    OrBuilder
    1.23
    GeneratedMessage
    1.23
    repeated
    1.20
    ;->
    1.14
    Proto
    1.11
     Proto
    1.10
     السياس
    1.09
     Pb
    1.09
    Activations Density 0.001%

    No Known Activations