© 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. 60508
    Prev
    Next
    INDEX
    Explanations

    function calls and initializations

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

    This neuron detects function or method invocation syntax (identifiers followed by “(”) 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
     presque
    -1.05
     notamment
    -0.96
     dépasser
    -0.93
    orin
    -0.90
    acknowled
    -0.89
     véhic
    -0.88
    بیش
    -0.88
    етесь
    -0.88
    々が
    -0.87
     رابطه
    -0.87
    POSITIVE LOGITS
     with
    2.44
     for
    1.77
     of
    1.64
     from
    1.58
     at
    1.56
     by
    1.53
    with
    1.32
     using
    1.09
     với
    1.06
     until
    1.02
    Activations Density 0.010%

    No Known Activations