© 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. 55893
    Prev
    Next
    INDEX
    Explanations

    water damage cleanup

    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
    maintenance
    -0.80
    Vincenzo
    -0.78
    Maintenance
    -0.77
     Poet
    -0.74
    ící
    -0.73
     inquiring
    -0.73
    Torino
    -0.73
     Ital
    -0.73
    ād
    -0.72
    provoking
    -0.72
    POSITIVE LOGITS
     restoration
    1.41
     Restoration
    1.17
     flood
    1.13
     restore
    1.13
     Mold
    1.10
     restored
    1.09
     mold
    1.08
     restores
    1.06
     cleanup
    1.05
     restoring
    1.02
    Activations Density 0.015%

    No Known Activations