© 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. 85458
    Prev
    Next
    INDEX
    Explanations

    questions or numbered lists

    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
     after
    -1.52
     Quien
    -1.34
    érieure
    -1.31
    "]:
    -1.29
    茛
    -1.28
    İyi
    -1.27
     this
    -1.26
    シップ
    -1.26
    forKey
    -1.23
    windowFixed
    -1.23
    POSITIVE LOGITS
    ’
    1.53
     estadia
    1.51
              
    1.50
          
    1.45
     largely
    1.38
     גם
    1.34
                    
    1.30
    1.30
    //
    1.30
     readily
    1.29
    Activations Density 0.015%

    No Known Activations