© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58164
    Prev
    Next
    INDEX
    Explanations

    US and other countries

    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
    Negative Logits
    '
    -2.05
    獁
    -1.73
    なんだろう
    -1.69
     Lokasi
    -1.68
    ambut
    -1.68
    をする
    -1.68
     Meningkatkan
    -1.67
    쨩
    -1.66
    眥
    -1.66
    这件事
    -1.64
    POSITIVE LOGITS
    s
    2.27
    er
    2.20
    in
    2.16
    la
    2.13
    j
    1.97
    f
    1.91
    os
    1.84
    en
    1.84
    ay
    1.80
    区别
    1.73
    Activations Density 0.045%

    No Known Activations