© 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. 29435
    Prev
    Next
    INDEX
    Explanations

    when making comparisons or judgments

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

    saving five credits

    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
    ផ្សេង
    0.44
     probablement
    0.41
     കാരണ
    0.40
     якобы
    0.40
     wzgl
    0.39
     Probably
    0.39
     Contrary
    0.38
    យ
    0.38
     下さい
    0.37
     unworthy
    0.36
    POSITIVE LOGITS
     عندما
    0.51
     when
    0.50
     ένα
    0.50
     وقتی
    0.50
     ketika
    0.49
     với
    0.49
     quando
    0.49
     гро
    0.49
     עם
    0.48
    毕竟
    0.48
    Activations Density 0.064%

    No Known Activations