© 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. 10-GEMMASCOPE-RES-131K
    4. 90824
    Prev
    Next
    INDEX
    Explanations

    enduring hardship or difficulty

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

    This neuron detects idiomatic expressions and words conveying tolerance or enduring something (e.g., “put up with,” “tolerate,” “stand and will not tolerate”).

    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
    of
    -1.56
    ULATION
    -1.45
     revenues
    -1.45
    郤
    -1.44
    i
    -1.44
    чно
    -1.42
    uchten
    -1.41
    剱
    -1.41
    ♯
    -1.36
    羕
    -1.36
    POSITIVE LOGITS
    These
    1.66
    </td>
    1.63
     jednost
    1.59
     качества
    1.59
    Dengan
    1.54
    př
    1.51
    這些
    1.49
     ИН
    1.49
    有些不
    1.49
     que
    1.47
    Activations Density 0.038%

    No Known Activations