© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 261300
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
    ence
    0.47
     महासचिव
    0.44
     Orleans
    0.44
    猬
    0.44
     Supervisory
    0.44
     Advice
    0.43
     SLAs
    0.43
     supervisory
    0.42
    ціа
    0.42
    ustain
    0.42
    POSITIVE LOGITS
    ים
    0.55
    𝚍
    0.55
    LINK
    0.52
     descoberta
    0.49
    дея
    0.49
     yeniden
    0.48
     tecnologías
    0.48
    ात
    0.47
    従来の
    0.47
    د
    0.47
    Activations Density 0.000%

    No Known Activations