© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1720
    Prev
    Next
    INDEX
    Explanations

    formal polite address

    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_40_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
    执行
    0.45
     eseguire
    0.45
    ครื่อง
    0.43
     실행
    0.43
    했어요
    0.43
    Requirements
    0.42
    DanhMucSP
    0.41
    }})
    0.40
    日で
    0.40
    ติดตั้ง
    0.40
    POSITIVE LOGITS
     respectfully
    0.79
     Minister
    0.61
     respectful
    0.60
     advocate
    0.58
     Opposition
    0.55
     minister
    0.53
     सदन
    0.52
     MINISTER
    0.52
     politely
    0.52
     gentleman
    0.51
    Activations Density 0.030%

    No Known Activations