© 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. 11645
    Prev
    Next
    INDEX
    Explanations

    abstract and introduction sections

    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
    myLabels
    0.52
     మైసూరు
    0.46
     العلماء
    0.43
    最优
    0.42
    Encoding
    0.42
    绻
    0.41
     定义
    0.41
     ምር
    0.40
     আদাল
    0.40
     определяет
    0.39
    POSITIVE LOGITS
     furtherance
    0.40
     verksam
    0.40
     undang
    0.40
     demeure
    0.39
     usher
    0.39
     milliard
    0.38
     \
    0.38
    យើង
    0.38
    ھ
    0.37
     Owing
    0.37
    Activations Density 0.006%

    No Known Activations