© 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. 27979
    Prev
    Next
    INDEX
    Explanations

    file directories css gradle mysql config

    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
     Jogos
    -1.13
    8
    -1.00
    jarah
    -0.99
     estoque
    -0.98
    teknik
    -0.98
     and
    -0.97
    Teknik
    -0.96
    Sådan
    -0.96
     avión
    -0.94
    Jawab
    -0.94
    POSITIVE LOGITS
     къде
    0.97
    喊道
    0.93
     kebersihan
    0.93
     Núñez
    0.91
     located
    0.90
     irrespective
    0.88
    感叹
    0.86
    ↙
    0.86
     keindahan
    0.86
     Архивировано
    0.86
    Activations Density 0.098%

    No Known Activations