© 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. 22-GEMMASCOPE-RES-131K
    7. 64738
    Prev
    Next
    INDEX
    Explanations

    contradiction and paradox

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

    The neuron strongly activates on occurrences of the word “contradiction” (and its close morphological variants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ⁛
    -1.31
     to
    -1.30
     Entfer
    -1.13
    enablog
    -1.13
     bardziej
    -1.13
     специфи
    -1.11
    又被
    -1.09
     spéciaux
    -1.09
    Abbildung
    -1.08
     одной
    -1.06
    POSITIVE LOGITS
     contradictions
    1.94
     contradiction
    1.88
     between
    1.65
     inconsistencies
    1.52
     inconsistency
    1.39
     contradict
    1.33
     contradic
    1.31
     противоре
    1.25
     contradictory
    1.24
    ↵
    1.23
    Activations Density 0.035%

    No Known Activations