© 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. 13113
    Prev
    Next
    INDEX
    Explanations

    code declaration or definition

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

    The neuron strongly activates on programming identifiers (especially CamelCase names) in source 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
     dokument
    -1.13
    فرم
    -1.11
     Cataluña
    -1.04
    
    -1.03
    lalu
    -1.03
    itoriale
    -1.01
    OON
    -1.01
     PLANNING
    -1.00
     nastro
    -1.00
     ปี
    -0.99
    POSITIVE LOGITS
     by
    1.16
     with
    1.07
     at
    0.98
    p
    0.93
    These
    0.91
    ve
    0.88
    しましたが
    0.86
    <bos>
    0.85
     these
    0.85
    これらの
    0.85
    Activations Density 0.011%

    No Known Activations