© 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. 22-GEMMASCOPE-RES-131K
    7. 36295
    Prev
    Next
    INDEX
    Explanations

    both, either, repetition

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

    The neuron is triggered by short, single‐letter identifiers (especially uppercase or mathematical variable names) in technical/math‐style contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    {})
    -0.96
    ()}}
    -0.90
    vų
    -0.88
     Ще
    -0.85
    (:,:,
    -0.83
    joit
    -0.83
    INC
    -0.82
    ഢ
    -0.81
     plomo
    -0.81
    ipc
    -0.81
    POSITIVE LOGITS
     both
    1.34
    both
    1.27
     både
    1.03
    BOTH
    1.01
     zarówno
    0.96
     beiden
    0.93
     sowohl
    0.92
    ทั้ง
    0.92
    两次
    0.90
    Both
    0.89
    Activations Density 0.046%

    No Known Activations