© 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. 58116
    Prev
    Next
    INDEX
    Explanations

    roles and characteristics of people

    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
     this
    -1.34
    this
    -1.25
     этом
    -1.14
     этих
    -1.09
     этой
    -1.06
    neue
    -1.05
     этого
    -1.02
    大好きです
    -1.02
    这种
    -1.01
    kapat
    -1.01
    POSITIVE LOGITS
     from
    1.13
    чера
    1.02
     who
    0.98
    CGSize
    0.98
    borough
    0.98
    将軍
    0.97
    Gemeinden
    0.96
     exhibition
    0.96
    paedia
    0.96
     meski
    0.94
    Activations Density 0.058%

    No Known Activations