© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9656
    Prev
    Next
    INDEX
    Explanations

    numbers and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    target in nums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🦃
    0.46
    க்கூட
    0.46
    OnOff
    0.45
     சா
    0.44
    Spots
    0.44
    علوم
    0.43
    ক্সি
    0.43
    Dramatic
    0.43
    轭
    0.43
    conductivity
    0.42
    POSITIVE LOGITS
    leetcode
    0.54
    TreeNode
    0.50
     ListNode
    0.47
     TreeNode
    0.47
    Leet
    0.46
     Rome
    0.43
    ListNode
    0.42
     Le
    0.41
     rome
    0.41
     n
    0.39
    Activations Density 0.002%

    No Known Activations