© 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. 70325
    Prev
    Next
    INDEX
    Explanations

    the followed by noun phrases

    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
    чего
    -0.96
     escrito
    -0.96
    '");
    -0.94
     masih
    -0.91
    філь
    -0.90
     yüzde
    -0.90
     sezonu
    -0.90
     hyvin
    -0.89
    وانی
    -0.89
    warran
    -0.89
    POSITIVE LOGITS
     default
    1.77
     ability
    1.61
     way
    1.55
     following
    1.48
     resulting
    1.39
     same
    1.36
     capability
    1.34
     functionality
    1.27
     underlying
    1.23
     inability
    1.23
    Activations Density 0.303%

    No Known Activations