© 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. 10937
    Prev
    Next
    INDEX
    Explanations

    immunoprecipitation, chain reaction, phosphorylated, supernatant

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

    scientific terminology and location references in academic papers, particularly related to medical and biological research.

    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
     you
    -1.12
    ：……
    -1.10
     are
    -1.09
     パソコン
    -1.05
     "
    -1.05
    全体的に
    -1.03
    食器
    -1.02
     is
    -1.01
    是你
    -0.99
    ながらも
    -0.98
    POSITIVE LOGITS
     each
    1.70
     насеља
    1.18
     Sloveniji
    1.17
    Each
    1.16
     nueva
    1.14
     każdej
    1.13
     or
    1.11
     Each
    1.09
     every
    1.08
    nyata
    1.08
    Activations Density 0.028%

    No Known Activations