© 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. 65777
    Prev
    Next
    INDEX
    Explanations

    screen time addiction

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numbers, numeric data, and quantitative tokens (e.g. digits, units, and related punctuation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     confidentiality
    -0.81
    DW
    -0.75
    ThroughAttribute
    -0.73
    穩定
    -0.73
     fisk
    -0.73
    HIV
    -0.72
    cccccccc
    -0.72
     diame
    -0.72
    ्रीय
    -0.72
    entación
    -0.71
    POSITIVE LOGITS
     screen
    2.16
     Screen
    1.91
     addiction
    1.84
     screens
    1.84
     addictive
    1.77
    screen
    1.75
    Screen
    1.73
     addic
    1.70
     SCREEN
    1.66
     Screens
    1.60
    Activations Density 0.042%

    No Known Activations