© 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. 17052
    Prev
    Next
    INDEX
    Explanations

    less than or equal to

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

    comparisons and conditions

    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
    第三
    0.43
    第三方
    0.42
     curtains
    0.41
    ктора
    0.41
    όν
    0.38
    έ
    0.38
    第二个
    0.38
     third
    0.38
    窗
    0.38
    óra
    0.38
    POSITIVE LOGITS
     बराबरी
    0.52
     >=
    0.50
     than
    0.48
     equals
    0.47
     inequality
    0.43
     برابر
    0.43
    逆に
    0.43
     equalities
    0.43
     equality
    0.42
     يساوي
    0.42
    Activations Density 0.013%

    No Known Activations