© 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. 103313
    Prev
    Next
    INDEX
    Explanations

    class or android UI controllers

    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
     intersper
    -0.91
    loginButton
    -0.88
    btnLogin
    -0.86
     juxtaposition
    -0.85
     버튼
    -0.83
    btnClose
    -0.83
    pictureBox
    -0.82
    handleClick
    -0.81
    ButtonClick
    -0.80
     yako
    -0.79
    POSITIVE LOGITS
     login
    1.90
     edit
    1.81
    Edit
    1.54
     Edit
    1.52
    Login
    1.43
    edit
    1.41
     Login
    1.41
     register
    1.39
     add
    1.36
     registration
    1.35
    Activations Density 0.155%

    No Known Activations