© 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. 258787
    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
     معاون
    0.47
    启
    0.46
    engk
    0.43
    越来越多的
    0.43
     fuck
    0.43
     فعال
    0.42
    翀
    0.40
     کیفیت
    0.39
    īng
    0.38
    培训
    0.38
    POSITIVE LOGITS
     multiport
    0.50
    fläche
    0.49
    𝓶
    0.49
     ríg
    0.47
    3
    0.47
     zas
    0.47
     vo
    0.46
    níky
    0.46
     calcula
    0.46
    <b>
    0.46
    Activations Density 0.001%

    No Known Activations