© 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. 22-GEMMASCOPE-RES-131K
    7. 73976
    Prev
    Next
    INDEX
    Explanations

    code identifiers and types

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

    The neuron is sensitive to numeric literals (digits) in code, i.e. it picks out numbers in source files.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     rurales
    -0.93
     tropicales
    -0.92
     konfig
    -0.92
    ření
    -0.91
     konsep
    -0.90
     Klä
    -0.87
     teñ
    -0.85
     startet
    -0.84
    Koordin
    -0.83
     reak
    -0.82
    POSITIVE LOGITS
     then
    1.02
    字
    0.92
     once
    0.86
    وق
    0.84
    之后
    0.82
    好多
    0.79
     затем
    0.78
     després
    0.77
    =$?
    0.77
    JF
    0.76
    Activations Density 0.007%

    No Known Activations