© 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. 31-GEMMASCOPE-2-RES-262K
    7. 53334
    Prev
    Next
    INDEX
    Explanations

    magnitude of potential drop

    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_31_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
     각
    0.49
     micrographs
    0.48
     인기
    0.47
     оказыва
    0.47
     در
    0.46
     청
    0.45
     intrig
    0.45
     ఉప
    0.45
     다니
    0.45
     κοινων
    0.45
    POSITIVE LOGITS
    for
    0.48
    r
    0.48
    は
    0.48
     change
    0.47
    фор
    0.47
    пе
    0.47
    प्रिंट
    0.47
    п
    0.46
     for
    0.46
    Point
    0.45
    Activations Density 0.001%

    No Known Activations