© 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. 34-GEMMASCOPE-RES-131K
    7. 81326
    Prev
    Next
    INDEX
    Explanations

    spdx license identifiers

    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_34/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
     Eddie
    -0.76
    FS
    -0.72
     ત
    -0.72
    ัฒ
    -0.69
    BorderFactory
    -0.69
     Kerr
    -0.69
     Ocean
    -0.68
     Employee
    -0.68
     Javier
    -0.68
     celebrities
    -0.67
    POSITIVE LOGITS
    Tener
    0.76
     Ludo
    0.75
    xuan
    0.73
     Tener
    0.69
    fullname
    0.68
    tigos
    0.68
     skul
    0.68
     Kyrgyz
    0.66
    lili
    0.66
     recette
    0.66
    Activations Density 0.061%

    No Known Activations