© 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. 1562
    Prev
    Next
    INDEX
    Explanations

    gender equality and roles

    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
     erwähnten
    -1.73
    ooplankton
    -1.68
    gemeente
    -1.57
    < 
    -1.47
     inspiração
    -1.46
    偲
    -1.46
     étan
    -1.43
    ￬
    -1.43
     bekämp
    -1.42
    珰
    -1.42
    POSITIVE LOGITS
     and
    1.95
     &
    1.71
     znajdziesz
    1.66
     in
    1.54
     —
    1.53
     другая
    1.48
    $-
    1.34
     swift
    1.30
     \
    1.29
    if
    1.27
    Activations Density 0.014%

    No Known Activations