© 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. 31195
    Prev
    Next
    INDEX
    Explanations

    resident evil game franchise

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

    The neuron strongly activates on mentions of video game titles and related proper nouns (e.g., “Resident Evil,” “Street Fighter IV,” “Bionic Commando”) and their platform or version markers.

    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
    MMA
    -0.74
    anches
    -0.73
     Seas
    -0.73
    긋
    -0.73
    nskap
    -0.72
     buro
    -0.72
     MMA
    -0.71
    ANDREW
    -0.71
    UNIDENTIFIED
    -0.70
     Galax
    -0.69
    POSITIVE LOGITS
     Umbrella
    1.38
     Raccoon
    1.35
     Capcom
    1.25
     STARS
    1.24
    Resident
    1.20
     Resident
    1.13
     zombies
    1.09
     zombie
    1.09
     Jill
    1.09
    Jill
    1.09
    Activations Density 0.012%

    No Known Activations