© 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. 48428
    Prev
    Next
    INDEX
    Explanations

    potentially controversial

    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
     Autodesk
    0.47
    За
    0.44
    ﹁
    0.44
    문제
    0.43
     ആശയ
    0.43
     समस्या
    0.43
    RSA
    0.42
     Lulu
    0.42
    ̜
    0.42
    𝐴
    0.42
    POSITIVE LOGITS
     kilometres
    0.44
     half
    0.44
     halfway
    0.43
     zelfs
    0.42
     kilos
    0.38
     kilometre
    0.38
     unbeatable
    0.38
    kilomet
    0.38
     meia
    0.37
     rasp
    0.36
    Activations Density 0.012%

    No Known Activations