© 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. 118120
    Prev
    Next
    INDEX
    Explanations

    from humble beginnings

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

    The neuron flags numeric and quantitative tokens—years, counts, sizes, and other numbers or metrics 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_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
     últimos
    -1.30
     recently
    -1.23
     recientemente
    -1.20
     recent
    -1.16
    Recently
    -1.09
    abinieri
    -1.08
    zőkönyv
    -1.02
     récemment
    -1.00
     terbaru
    -1.00
     lately
    -1.00
    POSITIVE LOGITS
     humble
    2.03
     modest
    1.59
     small
    1.58
     damals
    1.58
    small
    1.56
     тогда
    1.55
     then
    1.50
     niewiel
    1.40
     малень
    1.40
     скром
    1.38
    Activations Density 0.151%

    No Known Activations