© 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. 56724
    Prev
    Next
    INDEX
    Explanations

    sinking, sinking, sinkholes, subsidence

    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
    推广
    -0.77
     Jugendliche
    -0.77
     watersheds
    -0.75
     Spinning
    -0.75
     Yojana
    -0.75
    stroom
    -0.74
     Sorensen
    -0.74
     Disposable
    -0.74
     bifur
    -0.73
     ورق
    -0.73
    POSITIVE LOGITS
     subsidence
    2.03
     sinking
    1.65
     sink
    1.60
     settlement
    1.59
     Subs
    1.55
     settling
    1.48
    sink
    1.47
     Sink
    1.43
    Subs
    1.42
    subs
    1.34
    Activations Density 0.019%

    No Known Activations