© 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. 10-GEMMASCOPE-RES-131K
    7. 48150
    Prev
    Next
    INDEX
    Explanations

    increased [noun]

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

    The neuron specifically detects the word “increased.”

    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
    {
    -2.38
    e
    -2.17
    クソ
    -2.05
    賔
    -1.99
    er
    -1.98
    ねえ
    -1.96
      
    -1.94
    es
    -1.92
    le
    -1.88
    ㊂
    -1.84
    POSITIVE LOGITS
     increased
    2.66
    ୌ
    2.39
    玙
    2.36
    '
    2.34
    .
    2.23
    しようと
    2.16
    ENCIÓN
    2.11
    ⢅
    2.06
    風味
    2.05
     you
    2.03
    Activations Density 0.169%

    No Known Activations