© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111616
    Prev
    Next
    INDEX
    Explanations

    surprise or disbelief

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

    The neuron fires on occurrences of the word “believe” (including in contractions like “can’t believe”), i.e. expressions of surprise or disbelief.

    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
     Then
    -1.93
    大多
    -1.89
    大多数
    -1.77
    \
    -1.72
     også
    -1.70
     dédiée
    -1.61
     Whether
    -1.60
    ほとんど
    -1.57
     However
    -1.56
     Regarding
    -1.56
    POSITIVE LOGITS
    ↵
    1.43
     portail
    1.36
     WEDNESDAY
    1.36
    ねば
    1.35
     ilości
    1.33
     tremend
    1.32
     presidente
    1.31
     profes
    1.30
     luch
    1.30
     veter
    1.29
    Activations Density 0.005%

    No Known Activations