© 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. 34-GEMMASCOPE-RES-131K
    7. 77936
    Prev
    Next
    INDEX
    Explanations

    changing attributes

    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
     personalización
    -1.02
     manguera
    -1.02
     carcasa
    -0.97
     agujeros
    -0.94
    tudo
    -0.94
     premières
    -0.93
    ส่วน
    -0.93
     ngào
    -0.91
     ajutor
    -0.90
     comienzos
    -0.90
    POSITIVE LOGITS
     to
    3.45
     from
    1.78
     into
    1.35
     accordingly
    1.27
     değiştir
    1.05
     configuration
    1.04
    から
    1.00
     away
    1.00
     ownership
    0.98
     direction
    0.96
    Activations Density 0.099%

    No Known Activations