© 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. 28215
    Prev
    Next
    INDEX
    Explanations

    now or new

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

    The neuron fires on numeric tokens—especially version numbers, dates or other digits appearing in the text.

    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
     vė
    -0.90
    iç
    -0.87
    imbawa
    -0.85
     autre
    -0.84
    kuat
    -0.84
    lisle
    -0.84
     Besonder
    -0.84
    ʶ
    -0.83
    ਞ
    -0.83
     IndexPath
    -0.83
    POSITIVE LOGITS
     now
    3.17
     теперь
    2.63
     new
    2.59
     désormais
    2.28
     artık
    2.14
    新的
    2.02
     अब
    1.97
     Теперь
    1.96
    Теперь
    1.96
     newfound
    1.94
    Activations Density 0.173%

    No Known Activations