© 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. 13534
    Prev
    Next
    INDEX
    Explanations

    immunoglobulin and hepatocytes

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

    scientific or technical descriptions with specialized terminology.

    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
     ビッグ
    -0.95
    виа
    -0.94
    गी
    -0.94
     extérieurs
    -0.90
     Pál
    -0.89
     maman
    -0.88
    )　
    -0.87
     –
    -0.85
    zió
    -0.85
     terá
    -0.85
    POSITIVE LOGITS
    siębior
    1.02
    łąd
    1.00
     macetas
    0.97
    difice
    0.95
     производится
    0.95
    いただきました
    0.89
     estimé
    0.88
     melakukannya
    0.88
     from
    0.86
    ovým
    0.86
    Activations Density 0.439%

    No Known Activations