© 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. 31-GEMMASCOPE-2-RES-262K
    7. 1849
    Prev
    Next
    INDEX
    Explanations

    translates to cost savings

    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_31_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
     Legend
    0.46
    介绍
    0.46
    辂
    0.44
     对象
    0.44
     Ancient
    0.43
     Evolutionary
    0.43
     Dog
    0.43
    鸫
    0.43
    讲述
    0.42
     Semantic
    0.42
    POSITIVE LOGITS
     costs
    1.13
    costs
    1.08
     coûts
    0.96
    Costs
    0.93
     COSTS
    0.91
    cost
    0.91
    コスト
    0.91
     koszt
    0.89
     biaya
    0.88
     costos
    0.88
    Activations Density 0.201%

    No Known Activations