© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11311
    Prev
    Next
    INDEX
    Explanations

    code comments and numeric literals

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

    Looking at the activations, the neuron strongly activates on "cc1" (with activation values around 141-151), which appears in multiple contexts like "clang_cc1" in what appears to be C/C++ compiler test files. The neuron is looking for

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    橚
    -2.45
    婠
    -2.30
    ﮏ
    -2.13
     literario
    -2.11
     весна
    -2.06
    strategia
    -2.05
    的一声
    -2.03
     to
    -2.03
    culosis
    -2.02
     menú
    -2.02
    POSITIVE LOGITS
    at
    2.45
    9
    2.38
     Our
    2.14
    l
    2.14
    ">
    2.09
    as
    1.95
    7
    1.90
    ⡑
    1.79
     the
    1.73
    </strong>
    1.71
    Activations Density 0.016%

    No Known Activations