© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93199
    Prev
    Next
    INDEX
    Explanations

    buffs and effects

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

    The neuron is detecting mentions of game‐mechanic status effects or item/effect terminology.

    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
     EMERGENCY
    -0.88
    emergency
    -0.76
    acija
    -0.76
    bgcolor
    -0.76
     Zug
    -0.75
     oats
    -0.75
    衣裙
    -0.75
    Svara
    -0.73
    psychiat
    -0.73
    이스
    -0.73
    POSITIVE LOGITS
     buff
    1.68
    buff
    1.61
     applied
    1.57
     effects
    1.56
     effect
    1.47
     stacks
    1.43
    Buff
    1.42
    BUFF
    1.41
     buffs
    1.39
     Buff
    1.34
    Activations Density 0.011%

    No Known Activations