© 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. 864
    Prev
    Next
    INDEX
    Explanations

    Eur. J.Org. Chem.Cell. Signal

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

    citations in scientific or academic papers, particularly journal references with volume and page numbers.

    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
     your
    -1.62
     either
    -1.48
     Terima
    -1.45
     Resmi
    -1.44
     these
    -1.43
    PUESTA
    -1.36
     eget
    -1.34
     those
    -1.32
    tels
    -1.29
     pö
    -1.29
    POSITIVE LOGITS
     to
    1.86
     and
    1.33
    adalu
    1.31
     In
    1.30
     but
    1.29
     heutigen
    1.29
     War
    1.28
    brador
    1.21
     häufig
    1.20
     모든
    1.20
    Activations Density 0.031%

    No Known Activations