© 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-262K
    7. 228701
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Insertion
    0.42
    Train
    0.37
     spaghetti
    0.36
    Java
    0.35
    InstanceOf
    0.35
    ϲ
    0.35
    荼
    0.35
    Gesture
    0.35
    ieg
    0.35
     Cr
    0.35
    POSITIVE LOGITS
     izvor
    0.42
    skipped
    0.42
    rvGroup
    0.41
    ឪ
    0.40
     služ
    0.40
     необходимость
    0.40
     místě
    0.39
     شغله
    0.39
    absol
    0.39
    ۥ
    0.39
    Activations Density 0.006%

    No Known Activations