© 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. 34-GEMMASCOPE-RES-131K
    7. 90806
    Prev
    Next
    INDEX
    Explanations

    added and continuing

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

    The neuron fires on words that signal newness or emergence—terms like “new,” “added,” “emerge,” “keep,” “showing up,” etc., indicating recently appeared or continually occurring items.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     extensive
    -0.87
     excessive
    -0.87
     when
    -0.87
     spojen
    -0.86
     siquiera
    -0.86
    kolwiek
    -0.86
     خیلی
    -0.85
    所有
    -0.84
     finally
    -0.84
    시아
    -0.83
    POSITIVE LOGITS
    不断
    1.76
    contin
    1.62
     continually
    1.57
     continuamente
    1.51
     continues
    1.51
     constantly
    1.46
     continue
    1.45
     появля
    1.44
     continuously
    1.41
     постоянно
    1.40
    Activations Density 0.104%

    No Known Activations