© 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. 22-GEMMASCOPE-RES-131K
    7. 26497
    Prev
    Next
    INDEX
    Explanations

    unity tag, code block start

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

    This neuron strongly activates on the YAML anchor symbol (‘&’) used to define or reference aliases in serialized documents.

    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
    ↵↵
    -1.58
    什么
    -1.01
    UCHAR
    -1.01
    包含
    -1.01
    .*;
    -0.99
    ↵↵↵
    -0.98
    keits
    -0.93
    positivo
    -0.93
    ようになる
    -0.92
     {
    -0.90
    POSITIVE LOGITS
    Linki
    1.07
    ؾ
    1.01
     frågor
    1.00
    attet
    0.99
     olmad
    0.98
    excellents
    0.98
    戍
    0.96
     литров
    0.96
    raujo
    0.96
    uyer
    0.96
    Activations Density 0.000%

    No Known Activations