© 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-65K
    7. 5266
    Prev
    Next
    INDEX
    Explanations

    traditionally explained to predict

    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_65k_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
    телям
    0.53
     создание
    0.46
    ಿ
    0.45
    Future
    0.44
    рор
    0.44
     plethora
    0.43
     đáo
    0.42
     future
    0.41
     doomed
    0.41
    ギフト
    0.40
    POSITIVE LOGITS
    门口
    0.43
    榀
    0.40
     mention
    0.39
     Noting
    0.38
     Occupational
    0.37
     दिये
    0.36
    khov
    0.36
     Given
    0.36
    ണേ
    0.36
    公务
    0.36
    Activations Density 0.027%

    No Known Activations