© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4204
    Prev
    Next
    INDEX
    Explanations

    opponent or neighbor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    imo
    0.92
     কার্যক্রম
    0.91
     playoffs
    0.91
    elenggarakan
    0.90
     중심으로
    0.89
    combinations
    0.86
     electrolysis
    0.84
    ℍ
    0.83
    hyth
    0.83
     combinations
    0.83
    POSITIVE LOGITS
     opponent
    1.21
    相手
    1.14
    對方
    1.11
    对方
    1.09
    opponent
    1.05
    Neighbor
    1.03
     neighbor
    1.03
     Someone
    0.99
     vecino
    0.99
    对手
    0.94
    Activations Density 0.183%

    No Known Activations