© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100319
    Prev
    Next
    INDEX
    Explanations

    C string operations

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

    the period in `string.h` header includes in C code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects the dot in C/C++ header filenames (the “.h” part) in #include directives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    </u>
    -2.06
    ,"
    -1.47
     otras
    -1.45
     maioria
    -1.27
    ''
    -1.27
    ""
    -1.24
    )}
    -1.24
     garantizar
    -1.21
    */
    -1.21
    </h3>
    -1.21
    POSITIVE LOGITS
    </h2>
    1.57
    CURLOPT
    1.42
     medan
    1.39
     who
    1.35
     laterale
    1.33
    笵
    1.27
    ঐ
    1.27
     sinta
    1.25
    
    1.25
    calories
    1.24
    Activations Density 0.007%

    No Known Activations