© 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. 13502
    Prev
    Next
    INDEX
    Explanations

    SQL identifiers and labels

    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
     Dö
    0.55
     plug
    0.50
     प्रदान
    0.50
     rake
    0.48
     chopsticks
    0.48
     plank
    0.48
     b
    0.47
    
    0.47
     ples
    0.46
     paddle
    0.46
    POSITIVE LOGITS
    valuer
    0.60
    س
    0.58
    커
    0.55
     বাড়ি
    0.54
    ق
    0.52
    스의
    0.51
    ologues
    0.49
    스
    0.49
    Employees
    0.49
    الح
    0.48
    Activations Density 0.019%

    No Known Activations