© 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. 145987
    Prev
    Next
    INDEX
    Explanations

    uploading files

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

    years ago

    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
    希望
    0.52
     eventualmente
    0.48
     lanes
    0.47
     courts
    0.46
     hopes
    0.45
     Courts
    0.45
     管理
    0.45
    、
    0.44
    （
    0.43
     希望
    0.43
    POSITIVE LOGITS
     filmpje
    0.51
     kanker
    0.47
     книга
    0.45
     cartão
    0.45
    zął
    0.44
    柿
    0.44
     cairan
    0.44
     parâ
    0.43
     skillset
    0.43
    പ്പ്
    0.43
    Activations Density 0.001%

    No Known Activations