© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128072
    Prev
    Next
    INDEX
    Explanations

    dates and separators

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

    The neuron activates on parenthesized metadata—especially dates, source abbreviations, and other citation‐style information enclosed in parentheses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    t
    -1.98
    c
    -1.83
    s
    -1.80
    f
    -1.70
    le
    -1.63
    ni
    -1.59
    )
    -1.55
    de
    -1.53
    n
    -1.53
    lo
    -1.51
    POSITIVE LOGITS
     nimmer
    2.02
     heilig
    1.76
     Kedua
    1.61
     wandel
    1.59
     gekocht
    1.58
     treff
    1.55
    utusan
    1.55
    ༣
    1.54
     voren
    1.54
    ühner
    1.52
    Activations Density 0.017%

    No Known Activations