© 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. 22-GEMMASCOPE-RES-131K
    7. 70698
    Prev
    Next
    INDEX
    Explanations

    rooms and bathrooms

    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_22/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
     supone
    -1.04
     bevorzug
    -1.01
     سواء
    -0.98
     to
    -0.98
     types
    -0.96
     terá
    -0.95
    ailangan
    -0.95
     principalmente
    -0.94
     mücade
    -0.94
     особенно
    -0.93
    POSITIVE LOGITS
    Ales
    1.13
     ambiental
    1.12
    Buna
    1.00
    Ком
    1.00
     Viruses
    1.00
    Роз
    0.99
    Tahun
    0.94
     corpor
    0.94
    Обо
    0.94
    äste
    0.94
    Activations Density 0.001%

    No Known Activations