© 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. 10-GEMMASCOPE-RES-131K
    7. 130658
    Prev
    Next
    INDEX
    Explanations

    SpringBoot application classes

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

    The neuron fires on code identifiers (especially Java class or annotation names in CamelCase, e.g. “Application,” “Package,” “Properties”) rather than ordinary words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     by
    -1.64
     EconPapers
    -1.60
    ...)
    -1.59
     as
    -1.55
    厂商
    -1.52
     tradisi
    -1.47
     }\
    -1.46
     When
    -1.45
    挎
    -1.43
    ствует
    -1.42
    POSITIVE LOGITS
    8
    1.91
    6
    1.83
    4
    1.82
    <bos>
    1.79
    3
    1.77
    9
    1.70
    5
    1.60
    7
    1.52
    0
    1.49
     سانتی
    1.46
    Activations Density 0.001%

    No Known Activations