© 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. 22-GEMMASCOPE-RES-131K
    7. 13266
    Prev
    Next
    INDEX
    Explanations

    sixth nerve, MMP-9, boundary conditions

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

    notation and symbolic elements in technical documents, particularly in mathematical, scientific, and programming contexts.

    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_22/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
     tentando
    -0.94
    Ʋ
    -0.92
     uniquement
    -0.92
     kollek
    -0.91
     Chaque
    -0.90
     grotte
    -0.88
     trámites
    -0.88
    🧽
    -0.88
    鹪
    -0.87
     komfor
    -0.85
    POSITIVE LOGITS
     without
    0.88
     --
    0.88
    renched
    0.85
     any
    0.85
    hbase
    0.84
    ラインナップ
    0.83
     häls
    0.83
     kartą
    0.83
     to
    0.82
    Enums
    0.82
    Activations Density 0.073%

    No Known Activations