© 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. 59026
    Prev
    Next
    INDEX
    Explanations

    lens and its parts

    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
    ”
    -3.11
    
    -2.86
     Unlike
    -2.64
    儈
    -2.61
    ઁ
    -2.55
    瓩
    -2.53
    彣
    -2.52
    汭
    -2.52
    ペーン
    -2.50
     Notably
    -2.47
    POSITIVE LOGITS
    崀
    2.86
    \
    2.81
    </h2>
    2.72
     '
    2.70
      
    2.41
    暃
    2.39
     The
    2.38
    ቕ
    2.27
    菝
    2.23
    re
    2.22
    Activations Density 0.007%

    No Known Activations