© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76738
    Prev
    Next
    INDEX
    Explanations

    screen saver or display states

    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
    itación
    -0.84
    льники
    -0.80
    quias
    -0.77
    gean
    -0.77
     monop
    -0.76
    煦
    -0.75
     klat
    -0.74
     juft
    -0.73
    getVar
    -0.73
    Bootstrap
    -0.73
    POSITIVE LOGITS
     screens
    1.62
     Screens
    1.19
     wallpaper
    0.98
    screens
    0.94
     screen
    0.93
    Screens
    0.91
     protect
    0.88
     background
    0.79
    saver
    0.78
     bouncing
    0.76
    Activations Density 0.033%

    No Known Activations