© 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. 32822
    Prev
    Next
    INDEX
    Explanations

    things seen

    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
    ప్తి
    0.40
     themselves
    0.39
     Morris
    0.38
    互相
    0.38
    我們要
    0.38
    จะเป็น
    0.37
     መጠቀም
    0.37
    鈉
    0.37
     シルバー
    0.37
    会导致
    0.37
    POSITIVE LOGITS
    见过
    0.79
     countless
    0.78
    看过
    0.64
     decades
    0.64
     seen
    0.62
     décadas
    0.61
    多年的
    0.61
    无数
    0.61
     десятки
    0.58
     vuos
    0.58
    Activations Density 0.001%

    No Known Activations