© 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. 16-GEMMASCOPE-2-RES-262K
    7. 9104
    Prev
    Next
    INDEX
    Explanations

    sales and business contexts

    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_16_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
    م
    1.76
    し
    1.61
    在
    1.28
    و
    1.24
    يا
    1.20
    其他
    1.19
    ین
    1.16
    м
    1.16
    י
    1.15
    ב
    1.11
    POSITIVE LOGITS
     are
    1.14
    é
    0.93
    ફેદ
    0.91
    x
    0.90
    行う
    0.89
     at
    0.88
     as
    0.87
    sales
    0.86
    മൂഹ
    0.85
     aren
    0.84
    Activations Density 0.028%

    No Known Activations