© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100680
    Prev
    Next
    INDEX
    Explanations

    systems or materials

    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
     vektör
    -1.69
    有り
    -1.57
    ಝ
    -1.52
    饷
    -1.49
    Dicas
    -1.39
    Forrás
    -1.37
     kebersihan
    -1.35
    шенко
    -1.35
    During
    -1.34
    楽しめる
    -1.34
    POSITIVE LOGITS
     our
    1.89
    </strong>
    1.50
     your
    1.38
     another
    1.34
    ଂ
    1.34
     оста
    1.29
    我们
    1.29
    ﻷ
    1.27
     снова
    1.24
          
    1.23
    Activations Density 0.173%

    No Known Activations