© 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. 25946
    Prev
    Next
    INDEX
    Explanations

    RPG, GM, character rules

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

    This neuron fires on the author’s first‐person narrative statements (e.g. “I will be…”).

    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
    🧏
    -1.10
     Algorithms
    -1.10
     teori
    -1.09
     akus
    -1.08
    scheid
    -1.08
     subjek
    -1.07
    Algorithms
    -1.07
     Ekonomi
    -1.05
     konfer
    -1.03
    seiti
    -1.03
    POSITIVE LOGITS
     flavorful
    1.29
     player
    1.27
     rules
    1.25
     GM
    1.09
     players
    1.09
    player
    1.07
    gm
    1.06
     thematic
    1.05
     jugador
    1.04
     character
    1.02
    Activations Density 0.055%

    No Known Activations