© 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. 10-GEMMASCOPE-RES-131K
    7. 8262
    Prev
    Next
    INDEX
    Explanations

    #if defined, #define, inline

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

    The neuron is keyed to C/C++ preprocessor directives, especially conditional‐compilation lines like “#if defined(…)” and “#define.”

    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
     it
    -1.73
     erwor
    -1.67
     its
    -1.59
     them
    -1.47
     from
    -1.44
     his
    -1.41
    在這
    -1.38
     Kenntnis
    -1.38
    ugian
    -1.35
     gän
    -1.35
    POSITIVE LOGITS
     will
    1.46
    σης
    1.30
    前的
    1.26
     so
    1.23
     Dieser
    1.23
     podremos
    1.20
    dienne
    1.16
    érables
    1.14
     Richard
    1.13
     diverse
    1.13
    Activations Density 0.290%

    No Known Activations