© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107490
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tanpa
    -1.13
     Menggunakan
    -1.11
     Meningkatkan
    -1.05
     Perubahan
    -1.05
     Lakukan
    -1.02
     Ternyata
    -1.00
     Biaya
    -0.98
     Sekarang
    -0.98
     Berikut
    -0.97
     Terkait
    -0.97
    POSITIVE LOGITS
     anter
    1.04
     latter
    0.89
     separate
    0.85
     probab
    0.83
    面临
    0.82
    ه‌اند
    0.81
    更好地
    0.80
     отдель
    0.79
    ℒ
    0.79
    separate
    0.78
    Activations Density 0.140%

    No Known Activations