© 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. 103267
    Prev
    Next
    INDEX
    Explanations

    quoted strings and code elements

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

    The neuron is keyed up by the literal “\n” escape sequence inside quoted strings.

    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
     (
    -0.90
     unique
    -0.90
     when
    -0.89
     using
    -0.87
     joyas
    -0.85
     on
    -0.85
     small
    -0.85
     without
    -0.84
     while
    -0.84
     versatile
    -0.84
    POSITIVE LOGITS
     WQS
    0.95
     Mongol
    0.92
     ALC
    0.90
     operativa
    0.90
    <<<<<<<
    0.88
     cultur
    0.88
     inev
    0.88
    ދ
    0.87
     Andra
    0.87
     NTIS
    0.87
    Activations Density 0.003%

    No Known Activations