© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51512
    Prev
    Next
    INDEX
    Explanations

    states and characteristics

    np_acts-logits-general · gemini-2.5-flash-lite

    explaining complex multilingual topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loop
    0.56
    oped
    0.52
    immer
    0.52
    opf
    0.52
    Promotion
    0.50
    first
    0.48
    ן
    0.48
    ra
    0.46
    raction
    0.46
    older
    0.45
    POSITIVE LOGITS
     partielle
    0.55
     cette
    0.51
    的孩子
    0.51
     questa
    0.51
     বৈশিষ্ট্য
    0.51
    特徴
    0.49
     grâce
    0.49
     nell
    0.48
     ব্যথা
    0.48
     remercie
    0.48
    Activations Density 0.000%

    No Known Activations