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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90299
    Prev
    Next
    INDEX
    Explanations

    shear stress and force

    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
     クリア
    -1.38
    覿
    -1.38
     that
    -1.36
    ffeine
    -1.34
     BRITAIN
    -1.29
    酲
    -1.29
     ストレッチ
    -1.28
     BRASIL
    -1.27
     cerâmica
    -1.26
    他还
    -1.23
    POSITIVE LOGITS
     anderen
    1.31
     Makes
    1.30
    山上
    1.30
     Often
    1.27
    比如
    1.25
     Sometimes
    1.25
     TO
    1.23
     tenacious
    1.19
     treten
    1.16
     például
    1.16
    Activations Density 0.043%

    No Known Activations