© 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. 85061
    Prev
    Next
    INDEX
    Explanations

    epithelial to mesenchymal transition (EMT)

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

    medical and technical acronyms and abbreviations.

    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
    y
    -4.41
    —
    -2.77
    an
    -2.75
    er
    -2.72
    r
    -2.66
    v
    -2.66
     the
    -2.58
     was
    -2.53
    儅
    -2.50
    e
    -2.38
    POSITIVE LOGITS
    When
    2.58
    where
    2.55
    For
    2.55
    Only
    2.48
    There
    2.44
    The
    2.42
    }$
    2.41
    \
    2.34
    Although
    2.33
    新潟
    2.31
    Activations Density 0.002%

    No Known Activations