© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93213
    Prev
    Next
    INDEX
    Explanations

    project

    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
     hề
    -0.77
     馆
    -0.75
    ьи
    -0.74
     alertDialog
    -0.69
     wage
    -0.69
    ądz
    -0.69
    population
    -0.68
    ┈
    -0.68
    xaxis
    -0.68
    resser
    -0.67
    POSITIVE LOGITS
     project
    4.81
     Project
    3.91
     projects
    3.73
    Project
    3.55
    getProject
    3.50
    project
    3.42
    PROJECT
    3.17
     проек
    3.11
     PROJECT
    3.06
     projek
    2.95
    Activations Density 0.031%

    No Known Activations