© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72680
    Prev
    Next
    INDEX
    Explanations

    foreign language time words

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

    This neuron responds strongly to title‐case tokens in article headlines (i.e. words that appear in the headline).

    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
     now
    -2.50
     recently
    -2.42
     currently
    -2.27
     lately
    -2.22
     presently
    -1.88
     jetzt
    -1.80
     recent
    -1.77
     недавно
    -1.71
     yesterday
    -1.70
     latest
    -1.69
    POSITIVE LOGITS
     then
    1.73
     damals
    1.61
     тогда
    1.55
     salade
    1.39
     hongos
    1.34
     years
    1.32
     entonces
    1.28
     damaligen
    1.28
     famously
    1.28
     vuonna
    1.26
    Activations Density 0.142%

    No Known Activations