© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48824
    Prev
    Next
    INDEX
    Explanations

    common phrase starts

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

    The neuron detects large runs of whitespace used for code indentation or formatting.

    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
     Putting
    -0.80
     reinvent
    -0.75
    Cousin
    -0.75
    tikz
    -0.71
     nuestros
    -0.70
    グロー
    -0.70
     permanecer
    -0.70
     featuring
    -0.69
     putting
    -0.69
     jesteśmy
    -0.69
    POSITIVE LOGITS
     Doom
    0.96
    cisi
    0.96
    Poly
    0.88
    APOLIS
    0.88
    goat
    0.85
    Polygon
    0.85
     kW
    0.83
     ハンドバッグ
    0.82
     Mulligan
    0.82
    ┌
    0.82
    Activations Density 0.004%

    No Known Activations