© 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. 34-GEMMASCOPE-RES-131K
    4. 34687
    Prev
    Next
    INDEX
    Explanations

    thread makes

    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
     Finlande
    -0.88
     quarks
    -0.88
     Danemark
    -0.80
     Wrang
    -0.80
     Daven
    -0.80
     Lucha
    -0.79
     Pelicans
    -0.77
     hairdryer
    -0.77
     Waldorf
    -0.77
    ubility
    -0.77
    POSITIVE LOGITS
     global
    1.17
     step
    1.14
    global
    1.09
     GLOBAL
    0.99
     Global
    0.97
    step
    0.96
     batch
    0.96
    worldwide
    0.95
     Step
    0.93
     Batch
    0.92
    Activations Density 0.004%

    No Known Activations