© 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. 34-GEMMASCOPE-RES-131K
    4. 53958
    Prev
    Next
    INDEX
    Explanations

    my personal opinion/thoughts

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

    The neuron fires on self-referential, first-person expressions—especially “I,” “my,” “voice,” “opinion,” and related markers of the author sharing their own viewpoint.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    jutkan
    -0.88
    邃
    -0.88
    bours
    -0.84
    віти
    -0.83
    mbers
    -0.78
     цель
    -0.78
    rás
    -0.78
    setBounds
    -0.78
    گیرد
    -0.75
    olem
    -0.75
    POSITIVE LOGITS
     two
    2.06
    two
    1.73
    Two
    1.71
     cents
    1.69
    两
    1.58
     zwei
    1.53
     Two
    1.50
     двух
    1.48
     deux
    1.41
     $.
    1.38
    Activations Density 0.017%

    No Known Activations