© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9799
    Prev
    Next
    INDEX
    Explanations

    stem cell, branching logic

    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_16k_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
    諺
    0.39
    その
    0.38
    charges
    0.36
    ค้า
    0.36
    ้า
    0.36
    人の
    0.36
    بيقات
    0.36
     oj
    0.35
    規制
    0.35
    丑
    0.35
    POSITIVE LOGITS
     Branch
    1.02
     branched
    1.02
    Branch
    1.01
     branching
    0.99
     BRANCH
    0.96
    branch
    0.96
     branch
    0.95
     branches
    0.94
     Branches
    0.90
    分支
    0.86
    Activations Density 0.035%

    No Known Activations