© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60470
    Prev
    Next
    INDEX
    Explanations

    names like Emmanuel, Trinity, Emanuel

    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
     потрібно
    -0.77
     obligatorio
    -0.76
     Acknowledge
    -0.75
     BigNumberish
    -0.75
     老
    -0.72
     Pledge
    -0.72
     памят
    -0.72
    fuss
    -0.71
     true
    -0.71
    Lähde
    -0.70
    POSITIVE LOGITS
     Episcopal
    0.94
     Lutheran
    0.90
    NPS
    0.90
     UCC
    0.88
     episcopal
    0.87
     Vida
    0.86
    метра
    0.86
    ocin
    0.85
     Trinity
    0.84
    MIPS
    0.84
    Activations Density 0.012%

    No Known Activations