© 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. 75560
    Prev
    Next
    INDEX
    Explanations

    distinguish, district, disturb, distribute

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

    The neuron activates on tokens beginning with the letters “dist” (e.g. the “Dist” prefix in words like “Distinguish,” “District,” “Disturbing,” etc.).

    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
    1
    -3.64
    s
    -3.25
    With
    -3.22
    Because
    -2.92
    The
    -2.92
    After
    -2.91
    {
    -2.91
    2
    -2.89
    What
    -2.88
    When
    -2.78
    POSITIVE LOGITS
    玙
    3.08
    🧌
    3.03
    ୌ
    2.95
    埽
    2.83
    苹
    2.80
    镭
    2.73
    brakk
    2.72
     we
    2.72
     autre
    2.69
    蘼
    2.69
    Activations Density 0.004%

    No Known Activations