© 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. 221804
    Prev
    Next
    INDEX
    Explanations

    foreign, specialized, or scientific words

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

    copyrighted materials

    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
    受到
    0.46
    赔
    0.45
    的过程
    0.44
     lâng
    0.43
    एफआई
    0.42
     denies
    0.42
     denied
    0.42
     culminated
    0.41
    汀
    0.41
    રમાં
    0.41
    POSITIVE LOGITS
     inhomogeneities
    0.56
     homogeneity
    0.55
     восем
    0.55
    nove
    0.52
     நுண்ண
    0.52
    onycha
    0.51
     ஆயிர
    0.50
     Architektur
    0.50
     inhomogeneous
    0.49
    olytic
    0.48
    Activations Density 0.003%

    No Known Activations