© 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. 255922
    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
    Not in Any Lists

    No Comments

    Negative Logits
    מצא
    0.49
    কল্প
    0.48
    k
    0.47
    哪个
    0.47
    哪個
    0.45
     -(
    0.45
    ቁ
    0.45
     लैस
    0.45
     অন্তর্গত
    0.44
    خش
    0.44
    POSITIVE LOGITS
     Tapat
    0.58
     노트북
    0.56
     briefcase
    0.48
     공부해
    0.47
     책
    0.46
    Books
    0.46
     눈
    0.46
     macht
    0.45
     Handic
    0.45
    irst
    0.44
    Activations Density 0.001%

    No Known Activations