© 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. 10-GEMMASCOPE-RES-131K
    7. 73006
    Prev
    Next
    INDEX
    Explanations

    touchscreen display components

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

    The neuron fires on any token containing the substring “screen,” e.g. “touchscreen.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    \
    -2.36
     {
    -2.34
    </h3>
    -2.28
    L
    -2.19
    ge
    -2.14
     bumped
    -2.08
     oyuncak
    -2.05
    ￪
    -2.02
    🪆
    -2.00
     décision
    -1.96
    POSITIVE LOGITS
    erintah
    2.41
    寕
    2.30
    postsleuth
    2.16
    髎
    2.13
    푉
    2.06
     abrió
    2.02
    ஂ
    2.00
     ordenó
    1.99
     短发
    1.98
    灕
    1.98
    Activations Density 0.035%

    No Known Activations