© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 46332
    Prev
    Next
    INDEX
    Explanations

    zombie hordes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptuous
    0.43
    alogical
    0.43
    ♒
    0.43
    介入
    0.40
    鍗
    0.39
    ဿ
    0.39
     unsigned
    0.38
    alloy
    0.38
    小さ
    0.38
    Specular
    0.38
    POSITIVE LOGITS
     zombie
    2.91
     zombies
    2.75
     Zombie
    2.64
    Zombie
    2.56
     Zombies
    2.42
     undead
    2.05
    殭
    1.92
    ゾン
    1.80
    🧟
    1.80
    僵
    1.52
    Activations Density 0.012%

    No Known Activations