© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103123
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and licenses

    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
     their
    -0.87
     salpic
    -0.86
    عکس
    -0.86
    困惑
    -0.84
    tagena
    -0.83
     שה
    -0.82
    tierrez
    -0.81
     серый
    -0.81
     robar
    -0.80
    鞠
    -0.80
    POSITIVE LOGITS
     nepal
    0.94
     affez
    0.93
    totalPages
    0.91
     postes
    0.90
     there
    0.90
     fuc
    0.88
    Dela
    0.88
    acakt
    0.87
     hect
    0.85
    مئ
    0.85
    Activations Density 0.001%

    No Known Activations