© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2323
    Prev
    Next
    INDEX
    Explanations

    conversational language particles

    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
    ӳ
    0.55
    ামিটার
    0.48
     నుండి
    0.47
    Aloe
    0.47
    秚
    0.46
     खेलकर
    0.46
    烜
    0.45
    蜒
    0.44
     செய்யப்பட்ட
    0.44
    中使用
    0.44
    POSITIVE LOGITS
    ค่ะ
    0.51
    ,
    0.51
     แต่
    0.50
    ครับ
    0.47
    .
    0.47
    と思います
    0.46
     ,
    0.46
    는
    0.45
     사람들
    0.44
     그
    0.44
    Activations Density 0.019%

    No Known Activations