© 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. 31-GEMMASCOPE-2-RES-262K
    7. 156943
    Prev
    Next
    INDEX
    Explanations

    commitment, church, leader, average

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

    comparison or exceeding thresholds

    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_31_width_262k_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
    Bacteria
    0.48
     photons
    0.45
    המ
    0.44
    humans
    0.44
    長い
    0.43
     Bacteria
    0.43
     hundert
    0.43
    മ
    0.43
     naudoj
    0.42
     bâtiment
    0.42
    POSITIVE LOGITS
     एखा
    0.52
    一句
    0.52
    进来
    0.49
    类似于
    0.49
     чуть
    0.48
    জেল
    0.48
    表达式
    0.47
    或者
    0.47
    只是
    0.46
    相对
    0.46
    Activations Density 0.001%

    No Known Activations