© 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. 98888
    Prev
    Next
    INDEX
    Explanations

    places and environments

    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
     that
    -2.03
     which
    -1.91
     in
    -1.84
     if
    -1.56
    if
    -1.45
    4
    -1.38
    is
    -1.31
    3
    -1.31
    6
    -1.29
     for
    -1.25
    POSITIVE LOGITS
     שלנו
    1.43
    Dış
    1.41
    archiviato
    1.34
    Diweddarwch
    1.34
    EOUT
    1.34
    蓠
    1.32
     naší
    1.31
     nosso
    1.31
    cabulary
    1.27
    findpost
    1.27
    Activations Density 0.095%

    No Known Activations