© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31354
    Prev
    Next
    INDEX
    Explanations

    configuration updates

    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_40_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
     Mantra
    0.38
     mere
    0.38
    ITOR
    0.35
     पाठ
    0.34
     handic
    0.34
     Pah
    0.34
     проде
    0.34
    𝑣
    0.33
     Ú
    0.33
     Bride
    0.33
    POSITIVE LOGITS
    IfNeeded
    0.44
    وزیشن
    0.40
     लगते
    0.39
    выя
    0.38
    ady
    0.38
     ''){
    0.38
     लगती
    0.38
     konuştu
    0.38
     swoim
    0.37
    妵
    0.37
    Activations Density 0.013%

    No Known Activations