© 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. 34-GEMMASCOPE-RES-131K
    7. 48755
    Prev
    Next
    INDEX
    Explanations

    c/c++ preprocessor directives

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

    The neuron strongly activates on numeric literals (integer constants) in source code.

    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
    potensi
    -1.00
     then
    -0.81
     this
    -0.77
    guiar
    -0.77
    _'.$
    -0.70
     family
    -0.70
    clc
    -0.70
    ط
    -0.70
    三年
    -0.69
    剿
    -0.69
    POSITIVE LOGITS
    #
    2.89
     #
    2.72
     \#
    2.06
     $\#
    1.95
    \#
    1.89
    ＃
    1.83
    :#
    1.78
     '#
    1.70
     "#
    1.64
    +#
    1.63
    Activations Density 0.098%

    No Known Activations