© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106172
    Prev
    Next
    INDEX
    Explanations

    drug addiction, RPGs, following millennia

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

    The neuron fires on mentions of role-playing game jargon and titles—system names, RPG acronyms, and game-related proper nouns.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     compleja
    -0.90
    PHONY
    -0.75
    代价
    -0.71
     susceptibility
    -0.69
     vorgesch
    -0.69
     tháng
    -0.68
     Ведь
    -0.68
    ұ
    -0.67
     army
    -0.67
    discrimin
    -0.67
    POSITIVE LOGITS
     RPG
    0.86
     Referee
    0.84
     rpg
    0.83
    Setting
    0.81
     setting
    0.81
    默认
    0.79
     système
    0.79
     PCs
    0.78
    判定
    0.78
    一天
    0.78
    Activations Density 0.038%

    No Known Activations