© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11118
    Prev
    Next
    INDEX
    Explanations

    pride and proud

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

    The neuron flags expressions of personal pride or being proud (e.g. “proud,” “pride,” “proudly”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     അപകട
    0.63
    緩和
    0.62
    饨
    0.60
     위험
    0.59
     mutagen
    0.55
    朩
    0.55
     እንቅ
    0.54
    ॅमिली
    0.54
     inquiet
    0.54
    泠
    0.53
    POSITIVE LOGITS
     proud
    2.97
     pride
    2.86
     proudly
    2.86
    proud
    2.83
    Proud
    2.66
     orgull
    2.64
     Proud
    2.58
     자랑
    2.56
     orgullo
    2.45
     bragging
    2.34
    Activations Density 0.487%

    No Known Activations