© 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. 34-GEMMASCOPE-RES-131K
    7. 30363
    Prev
    Next
    INDEX
    Explanations

    PHP code comments, annotations

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

    This neuron fires on long runs of leading whitespace (indentation) 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_34/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
     мост
    -0.75
    麾
    -0.72
     paulo
    -0.68
    ViewType
    -0.67
    زین
    -0.66
     secondi
    -0.66
     Entwurf
    -0.66
     ہی
    -0.66
     partea
    -0.65
    選擇
    -0.64
    POSITIVE LOGITS
    /**
    2.02
     /**
    1.76
    /**
    1.23
    +/**
    1.02
     instanceof
    0.94
    assert
    0.82
     VizieR
    0.82
    ͈
    0.80
    setTextColor
    0.79
    __(/*!
    0.78
    Activations Density 0.019%

    No Known Activations