© 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-65K
    7. 49723
    Prev
    Next
    INDEX
    Explanations

    aka, breakdown, underrated

    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_65k_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
     Mitigation
    0.35
    负
    0.34
    呵呵
    0.33
     Luigi
    0.33
    吔
    0.33
    ইতি
    0.32
    тную
    0.32
    
    0.32
     aran
    0.31
     دیں۔
    0.31
    POSITIVE LOGITS
     donc
    0.38
     eum
    0.38
     constante
    0.37
     hence
    0.36
     Sá
    0.36
     certaines
    0.35
     mag
    0.35
     pronounce
    0.35
     prevail
    0.34
    ्रा
    0.34
    Activations Density 0.733%

    No Known Activations