© 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. 102190
    Prev
    Next
    INDEX
    Explanations

    plug and play, plugins, pluggable architecture

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

    the word "plug" (and its variations like "Plug" or "plug-in").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    that
    -2.52
     we
    -2.44
    they
    -2.39
    .
    -2.39
    릭터
    -2.22
    <strong>
    -2.16
     него
    -2.16
     kicking
    -2.11
     ながら
    -2.11
     exper
    -2.09
    POSITIVE LOGITS
    \
    2.88
    Fär
    2.72
     όταν
    2.64
    Alongside
    2.52
    غا
    2.52
     прошли
    2.50
    ]
    2.48
     pacto
    2.45
    
    2.44
    ではでは
    2.42
    Activations Density 0.005%

    No Known Activations