© 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. 40-GEMMASCOPE-2-RES-65K
    4. 702
    Prev
    Next
    INDEX
    Explanations

    last French King

    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
    
    0.23
     genomics
    0.22
     postdoctoral
    0.22
    trashItem
    0.22
     sightings
    0.22
     বাংলার
    0.22
    构建
    0.22
    <unused2058>
    0.22
    tLogRow
    0.21
     beragam
    0.21
    POSITIVE LOGITS
    6
    0.35
    7
    0.35
    8
    0.33
    3
    0.33
    9
    0.32
    2
    0.32
    5
    0.31
    4
    0.31
    0
    0.30
    1
    0.29
    Activations Density 0.264%

    No Known Activations