© 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. 31-GEMMASCOPE-2-RES-65K
    7. 16565
    Prev
    Next
    INDEX
    Explanations

    for learning and demonstrating

    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_65k_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
    uma
    0.46
    ιν
    0.41
    क्षिप्त
    0.40
    મા
    0.39
     ৭
    0.39
     ۱۳
    0.39
     отсут
    0.38
    వేశ
    0.38
     सामग्री
    0.37
     জর্জ
    0.37
    POSITIVE LOGITS
     hemodynamic
    0.44
     normalize
    0.43
     ensure
    0.43
    螟
    0.43
     robustness
    0.42
     behaviours
    0.41
     capire
    0.41
     wherever
    0.40
    asiswa
    0.40
     showing
    0.40
    Activations Density 0.007%

    No Known Activations