© 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. 10-GEMMASCOPE-RES-131K
    4. 70681
    Prev
    Next
    INDEX
    Explanations

    simply + verb

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

    The neuron fires on present-participle or infinitive action phrases that state intent or method (e.g. “trying to load,” “simply using,” “comparing…”).

    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
     Also
    -2.08
     Также
    -1.82
     también
    -1.66
    懸命
    -1.63
     También
    -1.57
    入った
    -1.52
    出来的
    -1.48
    もしっかり
    -1.45
    逡
    -1.45
     Também
    -1.43
    POSITIVE LOGITS
     will
    2.08
    蛧
    1.91
    ed
    1.83
    n
    1.64
    1
    1.62
     what
    1.59
    4
    1.59
    k
    1.56
     quicker
    1.50
     市場
    1.50
    Activations Density 0.028%

    No Known Activations