© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 16752
    Prev
    Next
    INDEX
    Explanations

    logical connectives and lists

    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
    లె
    0.38
     refrigerator
    0.37
    Computation
    0.37
    furniture
    0.37
     furniture
    0.36
     meubles
    0.36
    okkal
    0.36
    ު
    0.35
    лив
    0.35
    竰
    0.35
    POSITIVE LOGITS
     проник
    0.47
     они
    0.42
     ይሰ
    0.40
     вони
    0.40
    Λ
    0.40
     Where
    0.38
     Λ
    0.38
     Clos
    0.38
    📛
    0.38
     όπου
    0.37
    Activations Density 0.001%

    No Known Activations