© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 20136
    Prev
    Next
    INDEX
    Explanations

    legs, feet, tires, maintained, takes, characterized

    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
    上限
    0.46
     dealerships
    0.44
     आसानी
    0.43
    ^*$
    0.41
     ظاہر
    0.41
    图中
    0.40
    брав
    0.40
     eyew
    0.40
     случаях
    0.39
     उपयोगकर्ताओं
    0.39
    POSITIVE LOGITS
     pobre
    0.47
     survival
    0.43
     Grace
    0.42
                 
    0.41
    orable
    0.41
    感動
    0.41
     harus
    0.41
     creed
    0.40
    ↵↵
    0.40
             
    0.40
    Activations Density 0.017%

    No Known Activations