© 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. 66717
    Prev
    Next
    INDEX
    Explanations

    code and programming languages

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

    The neuron fires on the “dot” operator (period) used for member/property access 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_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
     the
    -1.04
    ！(
    -1.00
     própri
    -0.93
    啊啊
    -0.92
     Ewig
    -0.92
    ものである
    -0.91
     péro
    -0.91
    čník
    -0.90
    なきゃ
    -0.89
    Adapun
    -0.88
    POSITIVE LOGITS
     POM
    0.97
     Entscheidung
    0.95
     höheren
    0.94
     Российской
    0.93
    夸
    0.92
    觊
    0.91
    FTIR
    0.91
     kleineren
    0.90
    拦
    0.90
     veces
    0.88
    Activations Density 0.110%

    No Known Activations