© 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. 41806
    Prev
    Next
    INDEX
    Explanations

    fed up

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

    The neuron strongly activates on the phrase “fed up,” i.e. instances of that expression indicating annoyance or frustration.

    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
    Ꙭ
    -2.64
    ↵↵
    -2.41
    %，
    -2.25
    杙
    -2.23
    硤
    -2.19
     renowned
    -2.19
    $:
    -2.14
    黑色的
    -2.09
    をご覧ください
    -2.06
     白い
    -2.06
    POSITIVE LOGITS
     This
    2.44
    蜴
    2.44
    g
    2.42
    0
    2.36
     兩
    2.23
    What
    2.16
    丝毫
    2.13
     Using
    2.11
     tells
    2.09
     wants
    2.06
    Activations Density 0.003%

    No Known Activations