© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110952
    Prev
    Next
    INDEX
    Explanations

    code pointers and C/C++ datatypes

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

    The neuron is spotting numeric tokens (integer literals and digit sequences) in 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
     start
    -0.88
     robusto
    -0.78
     впервые
    -0.77
     times
    -0.75
     geh
    -0.72
     oldest
    -0.69
     compacta
    -0.69
     Nieder
    -0.68
     activities
    -0.68
     Rare
    -0.68
    POSITIVE LOGITS
    PP
    1.29
    pp
    1.24
     pp
    1.14
     PP
    1.09
     Pp
    1.08
    *&
    1.03
     discurso
    1.02
     MPP
    0.98
     PPS
    0.94
    Pp
    0.93
    Activations Density 0.010%

    No Known Activations