© 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. 84446
    Prev
    Next
    INDEX
    Explanations

    adding functions and methods

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

    The neuron fires on code tokens that name function or method calls (i.e. identifiers used in invocation positions like “add”, “append”, “register”, etc.).

    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
     vaak
    -1.10
     kaart
    -1.04
     リボン
    -1.03
    \
    -1.02
    ConfigureAwait
    -1.02
     autres
    -1.00
     meeste
    -0.99
     planten
    -0.98
     meestal
    -0.96
     Beton
    -0.95
    POSITIVE LOGITS
    Dzień
    1.11
    Jahre
    1.09
    ٦
    1.04
    amese
    1.03
    Юлия
    1.02
    Эк
    1.01
    óricas
    1.01
    Hình
    1.01
     nuevos
    1.00
     filho
    1.00
    Activations Density 0.005%

    No Known Activations