© 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. 22-GEMMASCOPE-2-RES-16K
    7. 3206
    Prev
    Next
    INDEX
    Explanations

    docstring explanations, usage, and robustness

    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_22_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
     drastic
    0.68
    <unused1886>
    0.68
    pans
    0.67
    ],\
    0.65
     அடு
    0.64
     smarter
    0.64
     fren
    0.62
     sharks
    0.62
    пон
    0.61
     silos
    0.59
    POSITIVE LOGITS
    <eos>
    1.01
     Therefore
    0.85
    `).
    0.82
    Therefore
    0.80
    ៕
    0.78
    விட்டது
    0.78
    のである
    0.76
    `.
    0.76
     Includes
    0.75
     عین
    0.75
    Activations Density 0.106%

    No Known Activations