© 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. 31236
    Prev
    Next
    INDEX
    Explanations

    Linux kernel system calls

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

    The neuron fires on programming‐language tokens—identifiers, symbols, and file‐path fragments typical of source code (e.g. struct, arrows “->”, pointer asterisks “*”, include paths, 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
    Biografie
    -0.76
     geworden
    -0.71
    quinone
    -0.69
     RANDOM
    -0.69
     governo
    -0.69
     Kardinal
    -0.68
    Defs
    -0.68
    jama
    -0.66
     cardíaca
    -0.65
     blogger
    -0.65
    POSITIVE LOGITS
    Process
    0.84
     PCB
    0.82
    灝
    0.77
     közel
    0.77
     Process
    0.75
    íslu
    0.74
    тове
    0.73
     task
    0.71
     tény
    0.71
    ってる
    0.71
    Activations Density 0.037%

    No Known Activations