© 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. 15701
    Prev
    Next
    INDEX
    Explanations

    relationships and connections

    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
     into
    -1.80
    ");
    -1.59
     in
    -1.41
     for
    -1.41
     to
    -1.33
    ख़
    -1.28
     this
    -1.25
    יוחד
    -1.17
     cristiano
    -1.16
     ratusan
    -1.14
    POSITIVE LOGITS
     regard
    1.46
    りましたが
    1.37
     behulp
    1.36
     Перейти
    1.32
    ᐕ
    1.29
     desplaz
    1.27
    ༡
    1.27
    ｃｍ
    1.23
    RICT
    1.23
    yyj
    1.23
    Activations Density 0.199%

    No Known Activations