© 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. 22-GEMMASCOPE-RES-131K
    7. 38611
    Prev
    Next
    INDEX
    Explanations

    temporal connectors

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

    This neuron responds to title-case or otherwise capitalized tokens, such as proper names, headings, and other title-style words.

    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
     also
    -1.18
    常常
    -1.08
    bestimmung
    -1.07
    也能
    -1.04
    기도
    -1.00
     BOTH
    -0.98
     ujar
    -0.97
    whelming
    -0.96
    égal
    -0.96
    ectores
    -0.96
    POSITIVE LOGITS
     after
    2.47
     після
    2.06
     после
    2.05
     setelah
    1.93
     After
    1.81
     לאחר
    1.77
    After
    1.70
    eafter
    1.66
    その後
    1.60
     then
    1.59
    Activations Density 0.012%

    No Known Activations