© 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. 34-GEMMASCOPE-RES-131K
    4. 86798
    Prev
    Next
    INDEX
    Explanations

    Crusades and related historical events

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

    The neuron strongly activates on the word “Crusade” (and its forms), effectively flagging mentions of the Crusades.

    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
    therin
    -0.88
     Bataille
    -0.79
    orp
    -0.79
     Presidential
    -0.77
    ᅵ
    -0.74
    buk
    -0.74
     والد
    -0.73
     Coffey
    -0.73
     Melayu
    -0.73
     Nigeria
    -0.72
    POSITIVE LOGITS
     Crusaders
    1.31
     crus
    1.23
     Crus
    1.16
    Crus
    1.13
     Outre
    1.03
     Crusader
    1.02
     Crusade
    0.97
     crusade
    0.89
    crus
    0.86
    十字
    0.82
    Activations Density 0.015%

    No Known Activations