© 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. 103780
    Prev
    Next
    INDEX
    Explanations

    settled down

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

    The neuron spots numeric expressions—particularly multi‐digit figures like years, census counts, measurements, and other full numbers.

    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
    ritual
    -0.79
    Sper
    -0.75
    pisah
    -0.73
     Eucharist
    -0.73
     Zeb
    -0.71
    ilever
    -0.69
    Eks
    -0.69
    exca
    -0.68
    諏訪
    -0.67
    gantung
    -0.66
    POSITIVE LOGITS
     settle
    4.81
     settling
    4.59
     settlement
    4.53
     settled
    4.38
     settles
    4.25
     settlers
    4.00
     Sett
    3.73
     settlements
    3.63
     SETTLE
    3.59
     settler
    3.56
    Activations Density 0.049%

    No Known Activations