© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64266
    Prev
    Next
    INDEX
    Explanations

    disillusionment and disappointment

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

    This neuron strongly activates on occurrences of the word “disillusion” (especially the form “disillusioned”).

    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
    τικός
    -0.88
     jealousy
    -0.84
    榦
    -0.82
     remonter
    -0.82
     schwach
    -0.81
    Comté
    -0.80
     خلق
    -0.79
     şimdi
    -0.78
    部は
    -0.78
    緊張
    -0.77
    POSITIVE LOGITS
     disillusion
    4.38
     disen
    3.13
     disappointment
    2.61
     disappointments
    2.19
     disappointed
    2.14
     разо
    1.88
    失望
    1.80
     disappoint
    1.61
     cynicism
    1.58
     illusions
    1.56
    Activations Density 0.048%

    No Known Activations