© 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. 22-GEMMASCOPE-RES-131K
    4. 84071
    Prev
    Next
    INDEX
    Explanations

    the way things are done

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

    The neuron specifically fires on occurrences of the phrase “the way” (often including the next word or two).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ᐈ
    -1.13
     paroisse
    -1.11
     belangrijke
    -1.05
     todėl
    -1.04
     keď
    -1.04
     olabilir
    -1.02
    흰색
    -1.02
     detalló
    -1.01
     reveló
    -1.00
    
    -1.00
    POSITIVE LOGITS
     ilk
    1.19
     tantas
    1.02
     manner
    1.02
     hoge
    1.02
     the
    1.01
    🤒
    1.01
     satte
    0.98
     outros
    0.98
    ∽
    0.97
     stille
    0.96
    Activations Density 0.021%

    No Known Activations