© 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. 34-GEMMASCOPE-RES-131K
    4. 38527
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting

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

    This neuron detects numeric escape sequences in strings—e.g. byte‐level escapes like “\x..”, “\123”, “%AB”, “\uXXXX” 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_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
     or
    -0.98
     дуб
    -0.82
     twelve
    -0.77
     enhanced
    -0.77
     unangemess
    -0.76
    权力
    -0.76
    艶
    -0.76
    ̗
    -0.76
    ixos
    -0.76
     Every
    -0.76
    POSITIVE LOGITS
    ꜰ
    0.97
     adipis
    0.91
     Suecia
    0.90
     trám
    0.88
     estimés
    0.88
    kost
    0.87
     mutlu
    0.87
     CAA
    0.86
    *-
    0.86
    LayoutParams
    0.85
    Activations Density 0.007%

    No Known Activations