© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59755
    Prev
    Next
    INDEX
    Explanations

    days through grades

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

    The neuron fires on numeric expressions—numbers, dates, quantities (e.g. “Monday,” “grades 9,” “four-year,” etc.).

    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
     of
    -0.94
    heets
    -0.77
     lại
    -0.77
     in
    -0.77
    ;
    -0.76
     durata
    -0.75
    erov
    -0.75
    reference
    -0.74
     first
    -0.73
    SESSION
    -0.73
    POSITIVE LOGITS
     through
    3.53
    through
    2.52
     thru
    2.45
    Through
    2.19
     através
    2.17
     attraverso
    2.14
     melalui
    2.09
    thru
    2.02
     через
    2.02
     Through
    2.02
    Activations Density 0.063%

    No Known Activations