© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54102
    Prev
    Next
    INDEX
    Explanations

    attractions place city splendid vast town

    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
     our
    -1.56
     new
    -1.48
     using
    -1.33
     vitally
    -1.12
     improvements
    -1.11
     increasingly
    -1.10
     tasty
    -1.08
     potentially
    -1.06
     newly
    -1.05
     ultimately
    -1.05
    POSITIVE LOGITS
     Dropdown
    1.16
     amalgam
    1.12
     Checkbox
    1.10
     manier
    1.09
     vouch
    1.05
    Instagram
    1.05
     Shutterstock
    1.05
    ถ้า
    1.04
     allé
    1.03
    БА
    1.02
    Activations Density 0.017%

    No Known Activations