© 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-262K
    7. 56890
    Prev
    Next
    INDEX
    Explanations

    Gettysburg Address and speeches

    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_262k_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
    互動
    0.45
    Sessions
    0.44
    咲
    0.43
    互动
    0.43
    展示
    0.41
     встречи
    0.41
    特
    0.41
     বৈঠক
    0.41
    带来了
    0.41
    瑪
    0.40
    POSITIVE LOGITS
     speech
    0.88
     भाषण
    0.81
     Speech
    0.80
     speeches
    0.77
    speech
    0.72
     exhort
    0.70
     paragraph
    0.67
     Paragraph
    0.65
    Speech
    0.63
     संबोधन
    0.63
    Activations Density 0.034%

    No Known Activations