© 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. 103081
    Prev
    Next
    INDEX
    Explanations

    total followed by a noun

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

    The neuron detects occurrences of the word “Total” (or “total”/“totals”)—typically where it labels or precedes a numeric count.

    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
    ↵↵
    -1.13
    satu
    -1.00
     Welche
    -0.98
    aie
    -0.98
    ihr
    -0.97
     позволяет
    -0.96
     trud
    -0.96
    Morgen
    -0.95
     fortement
    -0.95
    werden
    -0.95
    POSITIVE LOGITS
    itarianism
    1.55
    izers
    1.38
    izator
    1.25
    izer
    1.19
    částí
    1.13
    歼
    1.13
     букет
    1.09
     впечатление
    1.08
    leq
    1.07
    izing
    1.06
    Activations Density 0.014%

    No Known Activations