© 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. 1820
    Prev
    Next
    INDEX
    Explanations

    Fili and Philipp names

    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_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
    ↵↵
    -3.08
    '
    -2.63
     in
    -2.50
     
    -2.48
     What
    -2.38
     antics
    -2.30
     dedicate
    -2.28
    "
    -2.23
     Also
    -2.22
    <i>
    -2.20
    POSITIVE LOGITS
    菹
    3.14
    茕
    3.03
     saveiro
    2.84
     técn
    2.78
     camiset
    2.77
     लेकिन
    2.70
    襌
    2.66
     própri
    2.64
    鲥
    2.61
     vinil
    2.59
    Activations Density 0.001%

    No Known Activations