© 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. 34-GEMMASCOPE-RES-131K
    7. 30132
    Prev
    Next
    INDEX
    Explanations

    reporting speechreporting speech or possessive

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     in
    -1.05
    mıştır
    -1.04
     with
    -1.02
    本章
    -1.00
     for
    -0.98
     their
    -0.96
    ものは
    -0.96
     statunit
    -0.96
     обычно
    -0.96
     Decent
    -0.95
    POSITIVE LOGITS
     himself
    2.22
    himself
    1.52
     stesso
    1.36
     نفسه
    1.34
     fils
    1.30
    licitations
    1.27
    iamo
    1.26
    /</
    1.26
     jr
    1.21
     BROTHERS
    1.21
    Activations Density 0.076%

    No Known Activations