© 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. 47900
    Prev
    Next
    INDEX
    Explanations

    general formula representation

    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
     seemed
    -1.07
     began
    -1.06
     Almost
    -0.98
     уже
    -0.92
     using
    -0.91
     even
    -0.91
     Seems
    -0.90
     Many
    -0.89
     almost
    -0.89
     huge
    -0.87
    POSITIVE LOGITS
     independently
    1.05
     chacun
    1.04
     beter
    0.96
    klima
    0.95
     INDEPENDENT
    0.94
    represented
    0.91
    each
    0.89
     verbind
    0.88
     formules
    0.88
     each
    0.87
    Activations Density 0.037%

    No Known Activations