© 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. 16-GEMMASCOPE-2-RES-262K
    7. 31498
    Prev
    Next
    INDEX
    Explanations

    enemies and opponents

    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_16_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
    de
    1.11
    B
    0.94
    AN
    0.82
    َى
    0.80
    ي
    0.77
    ým
    0.76
    d
    0.75
    Worker
    0.73
    并不
    0.73
    us
    0.71
    POSITIVE LOGITS
     foes
    0.91
     opponents
    0.89
    л
    0.83
     adversaries
    0.82
     opponent
    0.81
     enemies
    0.81
     caricature
    0.77
     دشمن
    0.77
    ل
    0.77
     wisata
    0.76
    Activations Density 0.006%

    No Known Activations