© 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. 71689
    Prev
    Next
    INDEX
    Explanations

    dates or timestamps

    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
     demokra
    -1.10
     monstru
    -1.05
     batal
    -1.05
     valla
    -1.04
     péro
    -1.02
    Послед
    -1.02
    きましたが
    -1.02
     azulejos
    -1.02
     resili
    -1.01
     roca
    -1.01
    POSITIVE LOGITS
    meida
    0.99
    ceaux
    0.96
     Some
    0.95
     geçti
    0.91
     beach
    0.88
     moverse
    0.87
     behavior
    0.86
    裁
    0.85
     zwy
    0.85
     geldi
    0.85
    Activations Density 0.001%

    No Known Activations