© 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. 54149
    Prev
    Next
    INDEX
    Explanations

    screen, page, route, code

    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
     hingga
    -0.82
     These
    -0.79
     वर्ष
    -0.77
    辛い
    -0.75
     inclusion
    -0.74
    碰
    -0.72
     Arzneimit
    -0.71
    𝗽
    -0.71
     Sweeney
    -0.71
    epsfig
    -0.70
    POSITIVE LOGITS
     screen
    1.30
    creen
    1.24
    Screen
    1.18
     screens
    1.15
     pages
    1.13
     route
    1.03
     page
    1.02
    screens
    1.02
    Page
    1.00
    route
    1.00
    Activations Density 0.001%

    No Known Activations