© 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. 45451
    Prev
    Next
    INDEX
    Explanations

    translation, page tables, mapping

    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
     parejas
    -0.84
    rophes
    -0.74
     pareja
    -0.74
     избира
    -0.71
     Echo
    -0.71
    Общая
    -0.69
    Lips
    -0.68
    价
    -0.68
    African
    -0.68
    COC
    -0.68
    POSITIVE LOGITS
     VPN
    1.03
     vpn
    1.01
     PTE
    0.97
     fault
    0.96
     PT
    0.95
     miss
    0.91
     translation
    0.90
    vpn
    0.89
    fault
    0.88
     translations
    0.87
    Activations Density 0.035%

    No Known Activations