© 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. 76529
    Prev
    Next
    INDEX
    Explanations

    assignment and string concatenation

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

    The neuron fires on references to program variables (identifiers) being assigned or concatenated.

    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
    increase
    -0.79
     decrease
    -0.79
     promozione
    -0.74
    ՚
    -0.73
    なんですね
    -0.73
     Gambit
    -0.72
    と言える
    -0.71
    decrease
    -0.71
     uplands
    -0.71
     نشده
    -0.70
    POSITIVE LOGITS
     +=
    1.67
     .=
    1.11
     added
    1.01
     Append
    1.01
     appended
    0.98
     +
    0.98
     adding
    0.96
     նաև
    0.95
    append
    0.95
     append
    0.93
    Activations Density 0.009%

    No Known Activations