© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10547
    Prev
    Next
    INDEX
    Explanations

    remove unwanted decorations

    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_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
    нков
    0.46
    鳝
    0.44
     पॉजिटिव
    0.43
     মোটামুটি
    0.43
    морфи
    0.43
     Основ
    0.43
    itimate
    0.42
     умно
    0.41
     соответствует
    0.41
    eteen
    0.41
    POSITIVE LOGITS
     unwanted
    0.52
     decorations
    0.49
     border
    0.46
     borders
    0.44
     unnecessary
    0.44
    邊
    0.43
     ugly
    0.42
     baggage
    0.42
     headers
    0.41
     undesired
    0.41
    Activations Density 0.154%

    No Known Activations