© 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. 36438
    Prev
    Next
    INDEX
    Explanations

    comparison operators and identifiers

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

    This neuron detects numeric values or number literals (digits) in the 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_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
     dáms
    -1.82
     páns
    -1.68
    blå
    -1.65
     dámské
    -1.55
     剧照
    -1.55
    裥
    -1.52
     altijd
    -1.50
     vlasy
    -1.40
     doigt
    -1.38
    pumpe
    -1.35
    POSITIVE LOGITS
     not
    1.82
     didn
    1.68
     is
    1.62
     was
    1.59
     then
    1.41
     wasn
    1.37
     !=
    1.36
     were
    1.35
     >
    1.34
     are
    1.31
    Activations Density 0.026%

    No Known Activations