© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34110
    Prev
    Next
    INDEX
    Explanations

    association of, with or, facial movements

    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
     uren
    -1.16
     señores
    -1.15
     cristianos
    -1.05
     monstruos
    -1.02
    龕
    -1.02
    woord
    -1.00
     halen
    -0.99
    letics
    -0.96
     demonios
    -0.96
     flesta
    -0.94
    POSITIVE LOGITS
    Süd
    0.95
    Какие
    0.94
     remake
    0.94
    Når
    0.93
    Angebot
    0.93
    คือ
    0.93
    cribes
    0.93
     entweder
    0.91
    eynman
    0.91
     Memper
    0.91
    Activations Density 0.000%

    No Known Activations