© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12566
    Prev
    Next
    INDEX
    Explanations

    Eureka! CNN Validity Tribal Warrior

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

    This neuron activates on tokens inside programming code snippets—particularly the closing bracket of an array literal.

    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
     perú
    -1.27
    もうすぐ
    -1.23
     escritores
    -1.18
     escote
    -1.16
     incroy
    -1.16
    にほんブログ村
    -1.16
    を注文
    -1.15
     achet
    -1.14
     diminuer
    -1.14
     bolsos
    -1.13
    POSITIVE LOGITS
    y
    1.51
     to
    1.50
    u
    1.48
    on
    1.28
    b
    1.27
    p
    1.27
     y
    1.22
    ra
    1.20
    w
    1.16
    at
    1.15
    Activations Density 0.000%

    No Known Activations