© 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. 129374
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to occurrences of the word “unprecedented” (and its morphological variants) denoting an extreme or novel degree.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    unprecedented or unusually high degree

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ೢ
    -1.57
    蟜
    -1.55
    慫
    -1.53
     Handlungen
    -1.48
    ˕
    -1.39
    薷
    -1.38
    ୪
    -1.38
     wesentlichen
    -1.36
    ꔹ
    -1.35
    ícias
    -1.34
    POSITIVE LOGITS
     amounts
    1.81
     amount
    1.70
     levels
    1.59
    </b>
    1.49
    </h4>
    1.48
    s
    1.48
    (?)
    1.41
    ↵
    1.32
     number
    1.30
     thinks
    1.26
    Activations Density 0.025%

    No Known Activations