© 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. 260821
    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
    支撑
    0.47
     fiz
    0.43
     गुजरात
    0.41
    혔
    0.40
    筤
    0.40
     ingredient
    0.40
     cest
    0.39
    馳
    0.39
    位置
    0.38
     físicos
    0.38
    POSITIVE LOGITS
     प्रीवियस
    0.46
     bookstore
    0.46
    بعا
    0.46
    Harvest
    0.46
     consegn
    0.46
    harvest
    0.45
     broadcaster
    0.45
     bookstores
    0.44
    el
    0.43
    seign
    0.43
    Activations Density 0.001%

    No Known Activations