© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90636
    Prev
    Next
    INDEX
    Explanations

    health and HP stats

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

    numerical values representing player stats like health, power, level, or coordinates in game code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    nessed
    -0.85
    mique
    -0.77
    beach
    -0.74
    hotel
    -0.73
    SSS
    -0.72
    ofday
    -0.72
    tonsoft
    -0.71
    􏰀
    -0.71
    ptic
    -0.70
    gées
    -0.69
    POSITIVE LOGITS
     health
    4.28
    health
    3.17
     Health
    3.16
    Health
    3.00
     HP
    2.98
    HP
    2.78
     hp
    2.69
    HEALTH
    2.69
    hp
    2.53
     HEALTH
    2.42
    Activations Density 0.031%

    No Known Activations