© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2326
    Prev
    Next
    INDEX
    Explanations

    Russian legal and programming contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    􀂃
    0.39
     हेल्दी
    0.35
     κάτι
    0.34
     Decedent
    0.33
     cowboys
    0.33
     দারুণ
    0.33
     Cowboys
    0.32
    affeine
    0.32
    প্তাহ
    0.32
    ลูกค้า
    0.32
    POSITIVE LOGITS
     Ш
    0.27
     М
    0.27
     Д
    0.26
    с
    0.26
     Аб
    0.26
     У
    0.26
    М
    0.26
     С
    0.25
    С
    0.25
     Ма
    0.25
    Activations Density 6.819%

    No Known Activations