© 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-262K
    4. 30588
    Prev
    Next
    INDEX
    Explanations

    historical or financial obligations

    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
     stole
    0.48
     サ
    0.45
    スーツ
    0.42
     của
    0.41
    os
    0.41
     stacked
    0.40
     espionage
    0.40
     popped
    0.40
     sexy
    0.39
     brewed
    0.39
    POSITIVE LOGITS
    Historical
    0.43
    牖
    0.42
    裒
    0.41
     Twelfth
    0.41
     hearers
    0.41
    图书
    0.40
    辍
    0.40
     Init
    0.40
     computeEncoder
    0.40
     Listener
    0.39
    Activations Density 0.001%

    No Known Activations