© 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. 24186
    Prev
    Next
    INDEX
    Explanations

    online platforms like youtube and ebay

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

    youtube videos and tutorials

    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
    newspaper
    0.52
    レ
    0.50
    jc
    0.50
    не
    0.48
    editorial
    0.48
    Д
    0.48
    fastq
    0.47
    RON
    0.46
    newsletter
    0.46
     newsp
    0.46
    POSITIVE LOGITS
     किनारे
    0.47
     aplatis
    0.46
     Mechanic
    0.45
    ร้าง
    0.45
     dụng
    0.44
     nên
    0.43
    '
    0.43
     slidesToShow
    0.42
     给
    0.42
     Wali
    0.42
    Activations Density 0.033%

    No Known Activations