© 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-16K
    7. 924
    Prev
    Next
    INDEX
    Explanations

    physical attributes

    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_16k_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
     analysis
    0.46
     acquis
    0.46
     metadata
    0.44
     malware
    0.43
     Thesis
    0.43
     volatility
    0.43
     pursuant
    0.42
     $(
    0.41
     data
    0.41
     Analysis
    0.41
    POSITIVE LOGITS
     возле
    0.57
     деревя
    0.52
     drooping
    0.52
     вверх
    0.49
     пла
    0.48
     উঠিয়া
    0.47
    石头
    0.47
     ridges
    0.45
     glistening
    0.45
     малень
    0.45
    Activations Density 0.351%

    No Known Activations