© 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. 56217
    Prev
    Next
    INDEX
    Explanations

    alternative connectors

    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
    כה
    0.36
     pensa
    0.35
    न्दावन
    0.35
    rescent
    0.34
    ékek
    0.33
    дата
    0.33
    吔
    0.32
    institute
    0.32
    伫
    0.32
    咛
    0.32
    POSITIVE LOGITS
     aka
    0.63
     AKA
    0.55
    /
    0.50
     లేదా
    0.44
     তথা
    0.42
     Rég
    0.40
    /"
    0.38
     teh
    0.38
     yani
    0.38
     यानी
    0.37
    Activations Density 0.449%

    No Known Activations