© 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. 100032
    Prev
    Next
    INDEX
    Explanations

    LEGO bricks

    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
    marker
    0.48
     عق
    0.46
     subspace
    0.45
    pca
    0.43
    把它
    0.43
    t
    0.43
     cair
    0.42
    folg
    0.42
     inflection
    0.42
    ffiche
    0.42
    POSITIVE LOGITS
     mittlerweile
    0.50
     nicknamed
    0.49
     piş
    0.48
     图片
    0.48
    <unused545>
    0.47
     ITEM
    0.46
    たい
    0.46
     மூன்ற
    0.46
     முறையில்
    0.45
     mất
    0.44
    Activations Density 0.001%

    No Known Activations