© 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. 12407
    Prev
    Next
    INDEX
    Explanations

    discussing topics or states

    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
    「
    0.48
     tropes
    0.47
     gunakan
    0.42
     adopters
    0.41
    🫂
    0.41
    Already
    0.40
     usados
    0.40
     already
    0.39
    frastructure
    0.39
    拠
    0.39
    POSITIVE LOGITS
    却没有
    0.41
     widowed
    0.40
     математи
    0.40
     unlucky
    0.40
    错误
    0.39
    我们也
    0.39
    语文
    0.39
     tačiau
    0.39
    粈
    0.39
    فيف
    0.38
    Activations Density 0.013%

    No Known Activations