© 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. 41-GEMMASCOPE-2-RES-262K
    7. 5824
    Prev
    Next
    INDEX
    Explanations

    lean, leaning, leaned, leans

    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_all/layer_41_width_262k_l0_big
    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
    DEPTH
    0.49
     unidade
    0.49
    スム
    0.49
     molybdenum
    0.48
    钼
    0.48
    完善
    0.47
    LEVEL
    0.47
    照
    0.46
    相同的
    0.46
    功能的
    0.46
    POSITIVE LOGITS
     leaning
    1.17
     lean
    1.13
     Lean
    1.10
     leaned
    1.05
    Lean
    1.00
     leans
    0.99
    leaning
    0.98
    lean
    0.83
    Le
    0.71
     towards
    0.71
    Activations Density 0.008%

    No Known Activations