© 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. 68747
    Prev
    Next
    INDEX
    Explanations

    since the last

    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
    ではなく
    -1.45
     aislados
    -1.42
     creativos
    -1.33
     späteren
    -1.30
    ∽
    -1.29
     consideradas
    -1.28
    </strong>
    -1.27
    持つ
    -1.27
     without
    -1.24
    どのような
    -1.21
    POSITIVE LOGITS
     they
    1.74
     ${({
    1.35
    高
    1.34
    ۱۳
    1.28
    ْ
    1.27
     Теперь
    1.24
     Ș
    1.21
    是
    1.20
    可以
    1.20
     Januari
    1.20
    Activations Density 0.026%

    No Known Activations