© 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. 34-GEMMASCOPE-RES-131K
    7. 77852
    Prev
    Next
    INDEX
    Explanations

    code or foreign text identifiers

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

    The neuron is picking up Unicode escape sequences (e.g. “\uXXXX”) in text.

    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
    ʶ
    -0.90
     in
    -0.88
     йо
    -0.88
    اویر
    -0.87
     sehr
    -0.85
     on
    -0.85
     ambas
    -0.85
     sporad
    -0.85
     observa
    -0.84
     partially
    -0.78
    POSITIVE LOGITS
    complish
    1.06
     несколь
    1.02
    上記
    0.96
    vaila
    0.90
     zuhause
    0.90
     dargestellt
    0.89
    ourites
    0.88
    similar
    0.88
     zufrieden
    0.87
    ovsky
    0.87
    Activations Density 0.007%

    No Known Activations