© 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. 22-GEMMASCOPE-RES-131K
    7. 79964
    Prev
    Next
    INDEX
    Explanations

    Transitions Study, The Sir, Effects of, Thursday ,

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

    The neuron is specialized to detect the HTML “viewport” meta tag (i.e. the meta element setting `width=device-width, initial-scale=1`).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     should
    -1.21
     believes
    -1.13
     at
    -1.11
    ֶה
    -1.08
     from
    -1.06
     extérieure
    -1.05
    たとえば
    -1.03
     probably
    -1.03
     other
    -1.02
     five
    -1.02
    POSITIVE LOGITS
     crucial
    1.09
    toral
    1.05
     soooo
    1.03
     VERY
    1.01
     souvent
    1.00
    ,;
    1.00
    Mutability
    0.98
     BECAUSE
    0.98
    Gebruik
    0.97
     REALLY
    0.96
    Activations Density 0.000%

    No Known Activations