© 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-65K
    7. 3925
    Prev
    Next
    INDEX
    Explanations

    loan and repayment

    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_65k_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
    可以看到
    0.46
    明顯
    0.40
    沒有
    0.40
    仿佛
    0.39
    ლებიც
    0.39
    不僅
    0.38
    閎
    0.38
    簡單
    0.38
    かなり
    0.37
    變得
    0.37
    POSITIVE LOGITS
     kerjasama
    0.38
     repayment
    0.36
     সম্পর্
    0.34
     hospitality
    0.34
    DOCKED
    0.34
     repay
    0.34
     ransom
    0.34
    लेन
    0.33
     hostage
    0.33
     entreprises
    0.33
    Activations Density 0.004%

    No Known Activations