© 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. 620
    Prev
    Next
    INDEX
    Explanations

    C/C++ code and headers

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

    This neuron specifically detects the inclusion of the standard integer‐types header (i.e. “#include <stdint.h>” or the token “stdint”).

    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
     Objekt
    -0.69
     journaux
    -0.68
    cillos
    -0.67
    chit
    -0.66
    nóstico
    -0.65
    トゥ
    -0.65
    \}=\
    -0.64
     迷
    -0.63
     xrange
    -0.63
    กา
    -0.62
    POSITIVE LOGITS
     Gateway
    0.74
    BottomSheet
    0.71
    спу
    0.67
    ратор
    0.66
    getActiveSheet
    0.66
     Bola
    0.66
    ctuaries
    0.66
    échal
    0.65
     диск
    0.65
    orious
    0.65
    Activations Density 0.064%

    No Known Activations