© 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. 39494
    Prev
    Next
    INDEX
    Explanations

    medical therapies and treatments

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

    medications and medical treatments, particularly corticosteroids and other pharmaceutical therapies.

    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
    ,
    -1.07
     dollari
    -1.04
    −/−
    -1.02
    '
    -1.02
    новение
    -1.02
     situés
    -0.98
     वह
    -0.97
    áním
    -0.94
    撂
    -0.94
    頻繁
    -0.94
    POSITIVE LOGITS
     weeks
    1.43
    他们
    1.31
     sufficient
    1.25
     ObjectParameter
    1.23
     ģ
    1.21
     شروع
    1.20
    ٹر
    1.20
     pozor
    1.18
     ķ
    1.18
     combination
    1.18
    Activations Density 0.123%

    No Known Activations