© 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. 130523
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on tokens used in present-tense release or availability announcements (e.g. “new,” “now,” “out,” “available,” “released,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    now available or updated

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     then
    -1.35
    uktion
    -1.12
     soon
    -1.09
     später
    -1.07
     later
    -1.06
    emphas
    -1.03
     eventually
    -1.01
    ſſe
    -0.97
     затем
    -0.96
    彞
    -0.94
    POSITIVE LOGITS
    !
    1.48
     new
    1.47
     neuen
    1.23
     جدید
    1.17
     нового
    1.13
     updated
    1.12
     elér
    1.09
    new
    1.06
     added
    1.05
     дода
    1.02
    Activations Density 0.084%

    No Known Activations