© 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. 115540
    Prev
    Next
    INDEX
    Explanations

    Morley rank

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

    The neuron is looking for C/C++ preprocessor directive lines (e.g. #include, #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_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
    پیوند
    -0.73
     наказа
    -0.70
     suoi
    -0.69
    tanh
    -0.65
     toll
    -0.65
    unea
    -0.64
     Esses
    -0.64
    Abuse
    -0.63
     personnel
    -0.63
    amsmath
    -0.63
    POSITIVE LOGITS
    ео
    0.71
    ポリ
    0.68
     גל
    0.67
     transferencia
    0.66
    Robin
    0.65
    ី
    0.65
    tyka
    0.65
     GLAD
    0.65
     kub
    0.64
     Voters
    0.64
    Activations Density 0.063%

    No Known Activations