© 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. 105768
    Prev
    Next
    INDEX
    Explanations

    responsibility and choice

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

    The neuron fires on the phrase “up to you,” marking when the text places a decision or choice directly on the reader.

    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
              
    -1.64
     chris
    -1.62
    터
    -1.56
    ackerel
    -1.51
    ientôt
    -1.45
     صحيح
    -1.42
     intérêts
    -1.41
    finden
    -1.41
                            
    -1.40
     buscando
    -1.39
    POSITIVE LOGITS
     you
    1.94
     what
    1.83
     this
    1.79
    al
    1.79
    你来
    1.72
    ak
    1.68
     to
    1.52
    لمين
    1.46
    挨拶
    1.46
     обладает
    1.45
    Activations Density 0.016%

    No Known Activations