© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129757
    Prev
    Next
    INDEX
    Explanations

    The neuron highlights the document’s standout content words—rare technical terms, proper names, and other semantically informative tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    ellipsometry, Lady Gaga, x86, glutamate

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     all
    -0.87
    K
    -0.80
    csolódó
    -0.79
     hydrothermal
    -0.76
     distinctly
    -0.75
     bolster
    -0.75
     toho
    -0.74
     k
    -0.73
    콩
    -0.72
     hạnh
    -0.71
    POSITIVE LOGITS
     thuy
    1.02
    nachweise
    1.01
     január
    0.93
    cepts
    0.92
    beca
    0.88
    ›
    0.88
     eaters
    0.87
    Ⅶ
    0.86
    TRUNC
    0.86
     krach
    0.85
    Activations Density 0.120%

    No Known Activations