© 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. 60933
    Prev
    Next
    INDEX
    Explanations

    storage space and facilities

    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
    ⒝
    -0.95
     ordina
    -0.94
    ly
    -0.93
    硨
    -0.92
     épaules
    -0.91
     lj
    -0.90
     rist
    -0.89
     mao
    -0.89
    うわ
    -0.89
     filt
    -0.88
    POSITIVE LOGITS
     space
    1.59
     facilities
    1.42
     capacity
    1.37
     solutions
    1.36
     areas
    1.35
     compartments
    1.23
     facility
    1.22
     capabilities
    1.21
     solution
    1.20
     containers
    1.19
    Activations Density 0.027%

    No Known Activations