© 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. 18
    Prev
    Next
    INDEX
    Explanations

    Okay let's

    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
     annotations
    0.39
    を使用
    0.36
     warnings
    0.35
     remnants
    0.34
     encryption
    0.34
     usages
    0.34
     Applies
    0.34
    ，
    0.34
     HTTP
    0.33
     Contains
    0.33
    POSITIVE LOGITS
     ourselves
    0.48
     kijken
    0.44
     знаем
    0.42
    ujourd
    0.39
     કરીએ
    0.39
     başlayalım
    0.39
     хотим
    0.38
     tejto
    0.38
     цього
    0.38
    ogliamo
    0.38
    Activations Density 0.477%

    No Known Activations