© 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. 202841
    Prev
    Next
    INDEX
    Explanations

    defining orderings and contrasts

    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
    這麼
    0.53
     weren
    0.51
    ట్‌
    0.50
     всеки
    0.49
     blatantly
    0.48
     Dương
    0.47
     鞋
    0.46
     couldn
    0.46
    講解
    0.45
    ्रोल
    0.45
    POSITIVE LOGITS
     applications
    0.53
     bullet
    0.46
    حی
    0.45
    ٔ
    0.45
    akannya
    0.45
     manifold
    0.42
     sapp
    0.42
     constraints
    0.42
    ทร
    0.41
     appliquée
    0.41
    Activations Density 0.001%

    No Known Activations