© 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. 28512
    Prev
    Next
    INDEX
    Explanations

    purpose conjunctions

    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
    ,
    -0.99
    d
    -0.94
     with
    -0.89
    ίδ
    -0.88
    針對
    -0.87
    PENUTUP
    -0.86
     used
    -0.85
    0
    -0.84
    janje
    -0.84
     със
    -0.83
    POSITIVE LOGITS
     чтобы
    1.56
    使其
    1.33
     щоб
    1.30
    เพื่อ
    1.20
     to
    1.14
     để
    1.05
     so
    1.04
    Чтоб
    1.04
     כדי
    1.03
     inorder
    0.99
    Activations Density 0.189%

    No Known Activations