© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127948
    Prev
    Next
    INDEX
    Explanations

    stainless steel

    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
    Autoritní
    -1.62
    糅
    -1.52
     také
    -1.52
    痔
    -1.48
    人的
    -1.41
    {
    -1.41
    在
    -1.41
    嚳
    -1.40
    쫀
    -1.36
    垕
    -1.33
    POSITIVE LOGITS
    却不
    1.47
     ventaja
    1.40
    后者
    1.39
     atualmente
    1.37
    各大
    1.35
    ,
    1.32
     We
    1.27
    あらゆる
    1.27
     respectivas
    1.27
     integrado
    1.24
    Activations Density 0.004%

    No Known Activations