© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130208
    Prev
    Next
    INDEX
    Explanations

    The neuron detects the introductory phrases of numbered or itemized lists (e.g. “five things,” “eight factors,” “steps that,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    factors or items that are many, key, or selected

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    felizmente
    -1.11
     вагі
    -1.03
    няли
    -0.99
    timento
    -0.99
     нази
    -0.98
     начинают
    -0.96
    тора
    -0.94
    袄
    -0.94
     desactivar
    -0.94
    تنا
    -0.94
    POSITIVE LOGITS
     items
    1.37
     которые
    1.13
    が
    1.09
     typical
    1.08
     possible
    1.07
     avulla
    1.06
     које
    1.04
    
    1.02
    ỏi
    1.02
     plutôt
    1.01
    Activations Density 0.093%

    No Known Activations