© 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. 58343
    Prev
    Next
    INDEX
    Explanations

    researching and presenting studies

    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
     also
    -1.48
     также
    -1.35
     two
    -1.27
    simage
    -1.24
     even
    -1.22
     the
    -1.21
     compared
    -1.19
     those
    -1.16
     all
    -1.16
    捶
    -1.13
    POSITIVE LOGITS
    Keterangan
    1.42
     différents
    1.32
     étrang
    1.32
     görüntüsü
    1.32
     nabíz
    1.30
     chcete
    1.30
     görüntüleri
    1.29
    Sekarang
    1.29
     would
    1.28
     célè
    1.26
    Activations Density 0.811%

    No Known Activations