© 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. 84141
    Prev
    Next
    INDEX
    Explanations

    technical writer or director

    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
     When
    -2.70
     Когда
    -2.34
    鼉
    -2.11
     hábiles
    -2.06
     verir
    -1.99
    ヮ
    -1.98
    䨻
    -1.96
    
    -1.96
     攝
    -1.95
     όταν
    -1.94
    POSITIVE LOGITS
    ین
    2.22
    ㉗
    2.06
      
    2.02
    0
    1.99
    让他们
    1.93
     of
    1.92
     fled
    1.86
     that
    1.80
     オーバー
    1.78
    <strong>
    1.76
    Activations Density 0.000%

    No Known Activations