© 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. 120389
    Prev
    Next
    INDEX
    Explanations

    continuous learning

    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
    )[
    0.47
    ).[
    0.44
    DataAccess
    0.40
     extraer
    0.39
    劷
    0.39
     contener
    0.38
    InCM
    0.38
     autonomy
    0.38
     Эк
    0.37
     cardiomyocyte
    0.37
    POSITIVE LOGITS
    Problem
    0.45
     Problem
    0.39
    虎
    0.39
    animated
    0.38
    ﹀
    0.38
    Doom
    0.38
    SPL
    0.37
    悲
    0.37
    gad
    0.37
    Pain
    0.37
    Activations Density 0.001%

    No Known Activations