© 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. 29049
    Prev
    Next
    INDEX
    Explanations

    bed bugs

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

    references to beds in accommodation descriptions.

    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
     he
    -2.66
    ’，
    -2.00
    必要がある
    -1.94
    ですし
    -1.88
    ⡯
    -1.85
     realmente
    -1.84
    та
    -1.84
    was
    -1.77
    iree
    -1.77
    塒
    -1.73
    POSITIVE LOGITS
     begin
    1.96
     staunch
    1.91
     dengan
    1.90
     sculptor
    1.84
     його
    1.84
     WITH
    1.82
     лікування
    1.81
    شتر
    1.79
     restrict
    1.79
     What
    1.79
    Activations Density 0.005%

    No Known Activations