© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127922
    Prev
    Next
    INDEX
    Explanations

    inheritance of code and traits

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

    The neuron detects the word "inherited" and variations of inheritance concepts in programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron primarily activates on occurrences of the root “inherit,” i.e. words like inherit, inheritance, and inherited.

    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
    )
    -3.27
    ":
    -3.19
     \
    -2.73
    y
    -2.70
    i
    -2.67
    ي
    -2.61
     
    -2.55
     эту
    -2.53
    ('
    -2.50
    <em>
    -2.45
    POSITIVE LOGITS
    艫
    3.03
    摃
    2.94
    鰾
    2.75
    尨
    2.70
     概要
    2.69
    杙
    2.66
    ㌧
    2.63
    潆
    2.56
    踅
    2.53
    狆
    2.48
    Activations Density 0.004%

    No Known Activations