© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 70779
    Prev
    Next
    INDEX
    Explanations

    jur**

    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_31_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
    ක්ෂ
    0.54
    мся
    0.48
    ланти
    0.48
    bral
    0.47
    극
    0.46
    욤
    0.46
    ORTYPE
    0.46
    廻
    0.44
    طيني
    0.44
     сторона
    0.44
    POSITIVE LOGITS
     by
    0.46
     rights
    0.45
     Context
    0.45
     Mileage
    0.45
     Value
    0.44
     men
    0.44
     e
    0.44
     Men
    0.43
    men
    0.43
     jur
    0.43
    Activations Density 0.000%

    No Known Activations