© 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-16K
    7. 10770
    Prev
    Next
    INDEX
    Explanations

    areas of improvement or expertise

    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_16k_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
    ר
    0.75
    st
    0.71
    ك
    0.71
    أ
    0.71
    시
    0.69
    وس
    0.68
     أش
    0.66
     ط
    0.65
     cooks
    0.63
    ل
    0.63
    POSITIVE LOGITS
    areas
    0.99
     Bereichen
    0.97
     areas
    0.93
    Areas
    0.92
     영역
    0.90
    Area
    0.89
     områ
    0.89
     области
    0.87
    領域
    0.86
    områ
    0.84
    Activations Density 0.142%

    No Known Activations