© 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. 54292
    Prev
    Next
    INDEX
    Explanations

    software licenses and legal terms

    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
     Taking
    -0.94
     by
    -0.94
     after
    -0.91
     at
    -0.91
     leveraging
    -0.91
     lavish
    -0.90
     Quite
    -0.89
     remarkable
    -0.88
     for
    -0.86
     Trying
    -0.86
    POSITIVE LOGITS
    Kenya
    1.09
     barbati
    1.02
     ulei
    1.01
     opérateur
    1.01
    indicated
    0.99
    Convenient
    0.99
     chargeur
    0.98
    Mexico
    0.97
    Lake
    0.97
    primarily
    0.97
    Activations Density 0.001%

    No Known Activations