© 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. 31-GEMMASCOPE-2-RES-262K
    7. 38039
    Prev
    Next
    INDEX
    Explanations

    state or code

    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/layer_31_width_262k_l0_medium
    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
    ເພື່ອ
    0.48
    ানার
    0.47
    我们需要
    0.45
     ያስፈል
    0.45
    芑
    0.45
    利
    0.43
    可以让
    0.42
    సా
    0.42
    裒
    0.41
     কিভাবে
    0.41
    POSITIVE LOGITS
     engender
    0.57
     diretamente
    0.57
     congenital
    0.53
     directamente
    0.53
     direttamente
    0.52
     circunst
    0.50
     circunstancias
    0.50
     circumcision
    0.50
     fortuit
    0.50
     epid
    0.49
    Activations Density 0.012%

    No Known Activations