Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9348
    Prev
    Next
    INDEX
    Explanations

    winning competitions or contests

    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_22_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
    完毕
    0.93
    ნა
    0.85
     success
    0.81
    ிருந்து
    0.79
    cornell
    0.77
    }^{*}
    0.76
    ются
    0.76
    ة
    0.75
    }^{*}$
    0.75
    ාවේ
    0.74
    POSITIVE LOGITS
     wars
    1.20
     competitions
    1.12
     contests
    1.10
     battles
    1.07
     battle
    1.06
     сражение
    0.98
    battle
    0.96
     Battle
    0.96
     convincingly
    0.94
     gegründ
    0.92
    Activations Density 0.043%

    No Known Activations