© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28932
    Prev
    Next
    INDEX
    Explanations

    discourse markers indicating consequence or negation

    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
    ające
    0.46
    োর
    0.45
     грома
    0.44
    ご飯
    0.44
     অভিহিত
    0.44
    靂
    0.44
    ollary
    0.44
    GRESS
    0.43
    awcy
    0.43
    कर्मी
    0.42
    POSITIVE LOGITS
     জি
    0.49
    抑
    0.46
     neige
    0.42
    니
    0.41
     نها
    0.40
    瑜
    0.40
    тем
    0.39
    ني
    0.39
    钻石
    0.39
    besides
    0.39
    Activations Density 0.022%

    No Known Activations