© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23852
    Prev
    Next
    INDEX
    Explanations

    sequences forming words

    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_all/layer_41_width_262k_l0_big
    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
     einzelnen
    0.49
     স্বল্প
    0.46
     egyszer
    0.44
    一方面
    0.44
     één
    0.41
     禁止
    0.41
     peu
    0.41
    簧
    0.41
    iciencies
    0.41
    ToBounds
    0.41
    POSITIVE LOGITS
     chron
    0.48
     installment
    0.46
     instalment
    0.45
     closest
    0.45
    이자
    0.44
     onwards
    0.43
     available
    0.42
     listed
    0.42
     ever
    0.41
     подряд
    0.40
    Activations Density 0.003%

    No Known Activations