© 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. 83874
    Prev
    Next
    INDEX
    Explanations

    princess followed by titles

    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
     antemano
    -2.59
    ⦊
    -2.48
    </em>
    -2.48
     fared
    -2.31
     mußten
    -2.30
     wuß
    -2.17
    Ꮀ
    -2.08
    órico
    -2.05
    ,"
    -2.02
     gescha
    -2.02
    POSITIVE LOGITS
    媗
    2.53
    }
    2.45
    脔
    2.41
    ᠂
    2.39
     {
    2.36
    es
    2.36
     других
    2.36
     “(
    2.30
    斟
    2.28
    Según
    2.25
    Activations Density 0.002%

    No Known Activations