© 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. 40-GEMMASCOPE-2-RES-262K
    7. 15549
    Prev
    Next
    INDEX
    Explanations

    linked list and tree structures

    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_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
     upkeep
    0.44
    支部
    0.41
     déplacer
    0.41
     platelets
    0.40
    Pointing
    0.40
     lying
    0.39
    轭
    0.39
    حث
    0.38
     پیچھے
    0.38
     khel
    0.38
    POSITIVE LOGITS
     tree
    0.68
    TreeNode
    0.63
     TreeNode
    0.62
    tree
    0.56
     Tree
    0.56
     trees
    0.55
    树
    0.54
    나무
    0.53
    TREE
    0.52
     TREE
    0.52
    Activations Density 0.007%

    No Known Activations