© 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. 65422
    Prev
    Next
    INDEX
    Explanations

    consequences, misfortunes, tragedies, passionate

    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
    ット
    0.49
    預
    0.49
    最終
    0.48
     約
    0.45
     Erwach
    0.45
    使用
    0.45
    次
    0.45
     사용
    0.44
    
    0.44
    用い
    0.43
    POSITIVE LOGITS
     compartilhar
    0.48
    ayısıyla
    0.47
     tragedies
    0.46
     injustices
    0.45
     espíritu
    0.45
     bersih
    0.43
    दै
    0.43
     misfortunes
    0.41
    响
    0.40
     passionately
    0.40
    Activations Density 0.022%

    No Known Activations