© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5885
    Prev
    Next
    INDEX
    Explanations

    sort by key

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

    sorting lists

    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_53_width_65k_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
     वें
    0.40
     sustainably
    0.39
    াবহ
    0.39
    clickHandler
    0.38
     Marjorie
    0.38
    ございました
    0.38
    Mitchell
    0.38
    {//
    0.38
    elaide
    0.38
    вовано
    0.37
    POSITIVE LOGITS
    Sort
    0.45
     Sort
    0.45
    ToSort
    0.45
     sorts
    0.44
    赂
    0.44
    ByKey
    0.43
     compressed
    0.43
     numeric
    0.43
     Numeric
    0.43
    sort
    0.43
    Activations Density 0.000%

    No Known Activations