© 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. 10162
    Prev
    Next
    INDEX
    Explanations

    recognizing abbreviations and their definitions

    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
     Servers
    0.47
     ও
    0.46
    苏
    0.44
     quente
    0.43
     Sales
    0.41
     Allemagne
    0.41
    鸨
    0.41
    ป
    0.41
    合适的
    0.40
    льные
    0.40
    POSITIVE LOGITS
    ib
    0.50
    みて
    0.49
    incorrect
    0.49
    h
    0.49
    hea
    0.48
    provides
    0.46
    differ
    0.46
    at
    0.45
    ʔ
    0.45
    lden
    0.45
    Activations Density 0.068%

    No Known Activations