© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11495
    Prev
    Next
    INDEX
    Explanations

    wires are, Seminary American, vapour turbine

    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_10/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
     isra
    -1.20
     indiví
    -1.20
     classement
    -1.19
    多年的
    -1.19
    қы
    -1.18
    iações
    -1.17
     tudi
    -1.16
     mouseY
    -1.16
     passado
    -1.15
     STYLES
    -1.15
    POSITIVE LOGITS
     in
    1.43
    也可以
    1.25
     not
    1.25
     but
    1.24
     should
    1.19
    这句话
    1.19
    也可
    1.17
     can
    1.11
    不应该
    1.10
    numericUpDown
    1.09
    Activations Density 0.301%

    No Known Activations