© 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. 119764
    Prev
    Next
    INDEX
    Explanations

    docking

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

    The neuron detects the word "docking" and related terms in technical contexts about positioning or connecting objects.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    .
    -2.16
    lognese
    -1.96
    Werdegang
    -1.93
     Hinblick
    -1.92
    各样的
    -1.92
     寬
    -1.91
     帶
    -1.91
     來
    -1.85
     輕
    -1.84
    Глава
    -1.84
    POSITIVE LOGITS
    \
    2.56
    2.22
    ;"
    2.22
    "].
    1.91
    時代の
    1.89
    ;)
    1.88
    我跟
    1.86
     với
    1.86
    但我
    1.86
     vinh
    1.85
    Activations Density 0.003%

    No Known Activations