© 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. 40-GEMMASCOPE-2-RES-262K
    7. 211919
    Prev
    Next
    INDEX
    Explanations

    diverge, synthesize, French words

    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_40_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
    っている
    0.42
     という
    0.42
    Các
    0.40
    咵
    0.40
    称
    0.40
     Malays
    0.39
    ジャー
    0.39
    affa
    0.39
    クション
    0.37
    を含む
    0.37
    POSITIVE LOGITS
     diffé
    0.48
     diverge
    0.43
     synthesize
    0.42
     vendre
    0.41
     Diver
    0.39
    陨
    0.39
     maail
    0.39
     invest
    0.38
     pet
    0.38
    compiler
    0.38
    Activations Density 0.004%

    No Known Activations