© 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. 40-GEMMASCOPE-2-RES-262K
    7. 166799
    Prev
    Next
    INDEX
    Explanations

    Steps aligned

    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_40_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
     Fur
    0.45
     осигурање
    0.39
     ගැන
    0.39
     hydrogenation
    0.38
     Valuable
    0.38
    Fur
    0.38
     zucchero
    0.37
    鹼
    0.37
     riqueza
    0.37
     खेलने
    0.37
    POSITIVE LOGITS
     interfaces
    0.38
    作成
    0.37
    𝚂
    0.37
    defined
    0.37
    name
    0.37
     strutt
    0.37
    domains
    0.37
     চাই
    0.36
    域
    0.36
    CharField
    0.36
    Activations Density 0.000%

    No Known Activations