© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2149
    Prev
    Next
    INDEX
    Explanations

    Why It's So

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
    álního
    0.90
    Both
    0.80
     비슷한
    0.76
    営
    0.76
     Seorang
    0.75
    ่อน
    0.75
    ském
    0.74
    鷸
    0.74
    ovaná
    0.73
    而后
    0.72
    POSITIVE LOGITS
    0.85
    ACCESS
    0.84
     tools
    0.78
     pursuant
    0.77
     clays
    0.77
     workaround
    0.74
     cour
    0.73
    ),"
    0.73
     tactics
    0.73
     ph
    0.71
    Activations Density 0.149%

    No Known Activations