© 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. 68405
    Prev
    Next
    INDEX
    Explanations

    decks, patios, balconies

    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
    “
    -2.44
    椟
    -2.16
    .
    -2.11
    in
    -2.09
     Brought
    -2.05
    櫪
    -2.02
    ”
    -1.98
    ,“
    -1.92
     Become
    -1.88
    出声
    -1.88
    POSITIVE LOGITS
    沕
    2.47
    崀
    2.42
     большим
    2.25
    archiwizowane
    2.16
    i
    2.13
    Hrsg
    2.11
    Bahkan
    2.08
     deck
    2.08
     '
    2.03
    邶
    2.02
    Activations Density 0.002%

    No Known Activations