© 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. 244874
    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
     sirven
    0.46
    猙
    0.43
    ար
    0.41
     menyediakan
    0.41
     conocidos
    0.41
     "****
    0.40
     অভ
    0.40
     parall
    0.40
     cumpl
    0.40
     cumple
    0.39
    POSITIVE LOGITS
     strictest
    0.45
    성
    0.45
    Triplet
    0.45
     Imports
    0.44
    OURCES
    0.44
     коль
    0.44
     الث
    0.44
    CRET
    0.44
    RATE
    0.43
    ocolate
    0.43
    Activations Density 0.002%

    No Known Activations