© 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. 4736
    Prev
    Next
    INDEX
    Explanations

    Key improvements and explanations

    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
    没了
    0.38
    引号
    0.38
    
    0.35
     spaceShip
    0.34
    жны
    0.33
     analogues
    0.33
     मद्देनजर
    0.32
    elfalt
    0.32
     polymers
    0.32
    щими
    0.32
    POSITIVE LOGITS
     première
    0.43
     kutoka
    0.41
     pertama
    0.39
    8
    0.39
     starting
    0.39
     પારિજા
    0.38
     questo
    0.38
    が出
    0.38
     chụp
    0.38
     gồm
    0.38
    Activations Density 0.066%

    No Known Activations