© 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. 40-GEMMASCOPE-2-RES-65K
    7. 1246
    Prev
    Next
    INDEX
    Explanations

    class and classification

    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_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
    credible
    0.49
    闓
    0.46
    ultur
    0.46
    }{$
    0.45
     fudge
    0.44
     Zar
    0.39
     idée
    0.38
    拴
    0.38
     asymptotically
    0.37
     hahaha
    0.37
    POSITIVE LOGITS
     Class
    0.93
     class
    0.80
     kelas
    0.74
    class
    0.74
    ifications
    0.74
    ifiable
    0.73
     CLASS
    0.73
    クラス
    0.71
    Class
    0.71
     classe
    0.71
    Activations Density 0.044%

    No Known Activations