© 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. 202979
    Prev
    Next
    INDEX
    Explanations

    initial context and multilingual terms

    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_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
     总
    0.47
    swarm
    0.43
     ,
    0.42
    我可以
    0.42
     لها
    0.41
     बोली
    0.41
     forstå
    0.41
    行業
    0.41
     Glück
    0.40
     vermutlich
    0.39
    POSITIVE LOGITS
     acudir
    0.43
     завое
    0.42
     conco
    0.42
    先端
    0.42
    ುನ
    0.41
    ğinin
    0.41
    컬
    0.41
     Roder
    0.40
    MDET
    0.40
     practic
    0.40
    Activations Density 0.002%

    No Known Activations