© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1685
    Prev
    Next
    INDEX
    Explanations

    Pb, fiduciary duty, gdb command

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

    The neuron activates on isolated domain‐specific keywords or acronyms—single tokens like “fumble,” “GraphQL,” or the chemical symbol “Pb.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Sekarang
    -2.61
    Kondisi
    -2.53
    
    -2.42
    Hanya
    -2.38
    襌
    -2.36
    Spesifikasi
    -2.34
    9
    -2.34
     برای
    -2.33
     Its
    -2.33
    Fungsi
    -2.31
    POSITIVE LOGITS
    er
    2.50
     for
    2.36
    a
    2.16
    𓋼
    2.11
    ه
    2.08
    K
    2.03
    朏
    2.02
    F
    2.02
    掟
    2.02
     
    2.00
    Activations Density 0.002%

    No Known Activations