© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108325
    Prev
    Next
    INDEX
    Explanations

    print statements

    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_34/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
     tilby
    -1.05
    them
    -1.02
    łem
    -1.01
    お楽しみに
    -1.01
    ufficient
    -0.99
     preparado
    -0.99
    Those
    -0.98
     forcé
    -0.97
     tervez
    -0.97
     accidentes
    -0.96
    POSITIVE LOGITS
     dokonce
    1.23
    なので
    1.07
    ﹋
    1.03
    とは言
    1.02
    Gente
    1.02
     formate
    1.00
    Zdrav
    0.96
     hecta
    0.94
     Люди
    0.94
     رسانی
    0.94
    Activations Density 0.016%

    No Known Activations