© 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. 69349
    Prev
    Next
    INDEX
    Explanations

    class extends

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

    The neuron detects Java class inheritance declarations by spotting the “extends” keyword.

    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
     使っ
    -2.72
    }$
    -2.56
    𓐍
    -2.33
     på
    -2.25
    </strong>
    -2.14
    柺
    -2.13
    雷霆
    -2.13
    udadera
    -2.11
    」　
    -2.09
     has
    -2.08
    POSITIVE LOGITS
    5
    2.73
    1
    2.72
    “
    2.70
    乄
    2.59
    The
    2.53
     Our
    2.44
    咴
    2.44
    が
    2.42
     spezielle
    2.42
     hochwertige
    2.42
    Activations Density 0.013%

    No Known Activations