© 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. 228346
    Prev
    Next
    INDEX
    Explanations

    domain of, book deal, world class

    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
    Ngày
    0.45
     আবিষ্কার
    0.44
    ']],
    0.43
    骑
    0.43
    ën
    0.43
    房间
    0.42
    헉
    0.42
    Robert
    0.41
    傗
    0.41
    绁
    0.40
    POSITIVE LOGITS
     키
    0.50
     terrestrial
    0.50
     Northern
    0.47
     カ
    0.47
     ዓ
    0.47
    твори
    0.47
     DAC
    0.46
     kitt
    0.45
    取り
    0.45
     प्रत्यक्ष
    0.45
    Activations Density 0.001%

    No Known Activations