© 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. 130390
    Prev
    Next
    INDEX
    Explanations

    learning from

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

    The neuron is highly activated by expressions of “learn from,” i.e. it detects occurrences of the phrase indicating learning from someone or something.

    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
     Another
    -2.08
    ’
    -1.93
    ichteten
    -1.83
    🕗
    -1.73
    ка
    -1.73
     in
    -1.72
    ichtete
    -1.64
        
    -1.59
     Other
    -1.57
     Event
    -1.57
    POSITIVE LOGITS
    艄
    1.88
     墊
    1.87
    ٴ
    1.84
    镡
    1.80
    
    1.76
     знал
    1.75
    :"#
    1.74
    ̣i
    1.74
    攆
    1.73
     eachother
    1.72
    Activations Density 0.014%

    No Known Activations