© 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. 80733
    Prev
    Next
    INDEX
    Explanations

    numerical sequences dates years

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

    The neuron spikes on Markdown-style image/embed links (e.g. the “![](… )” tokens and associated filename fragments).

    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
    ૉ
    -1.23
    HttpEntity
    -1.04
     可愛い
    -1.01
    ΰ
    -1.00
    儚
    -0.95
    𓂂
    -0.94
    isGrid
    -0.92
     ñ
    -0.92
    研发
    -0.91
     descobri
    -0.90
    POSITIVE LOGITS
     lecker
    1.22
     насеља
    1.14
     растений
    1.05
     contemporary
    1.04
    𝗼
    1.03
     इत
    0.98
    цыі
    0.97
     hesitation
    0.97
     растения
    0.96
     passions
    0.94
    Activations Density 0.004%

    No Known Activations