© 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. 23640
    Prev
    Next
    INDEX
    Explanations

    addAction or add

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

    The neuron fires on occurrences of the keyword “function” (i.e. when detecting function definitions or invocations 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
     Meningkatkan
    -0.85
    ạm
    -0.85
     pondok
    -0.83
     niega
    -0.83
     được
    -0.79
     mantend
    -0.79
     mengembangkan
    -0.79
    获得
    -0.78
     پودر
    -0.77
     betreft
    -0.76
    POSITIVE LOGITS
     add
    1.03
     adder
    1.00
    addAction
    0.88
     adding
    0.86
     function
    0.84
    フィルター
    0.83
     spraw
    0.82
    oplus
    0.81
    add
    0.81
    Add
    0.79
    Activations Density 0.016%

    No Known Activations