© 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. 34-GEMMASCOPE-RES-131K
    7. 4215
    Prev
    Next
    INDEX
    Explanations

    #include followed by .h

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

    This neuron sharply activates on C/C++ code tokens—especially identifiers (e.g. class and variable names), preprocessor directives, and syntax punctuation.

    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
    rrggbb
    -0.94
    Ār
    -0.87
     conftest
    -0.86
    ÈNE
    -0.82
    humanité
    -0.77
    prefs
    -0.76
     suhu
    -0.75
     intervenciones
    -0.75
     umumnya
    -0.75
    ruiter
    -0.74
    POSITIVE LOGITS
     DirectX
    1.25
     nullptr
    1.24
     Direc
    0.91
     arac
    0.90
    ()->
    0.88
    pagnes
    0.88
    ]->
    0.87
    _->
    0.86
     SDLK
    0.86
     kated
    0.86
    Activations Density 0.017%

    No Known Activations