© 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. 16-GEMMASCOPE-2-RES-262K
    7. 47551
    Prev
    Next
    INDEX
    Explanations

    weight of

    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_16_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
     مارس
    0.59
     чуть
    0.59
    terus
    0.59
    ób
    0.58
    mlst
    0.58
    <unused42>
    0.58
     картины
    0.57
    峼
    0.57
    ော်
    0.57
     እንቅስቃሴ
    0.57
    POSITIVE LOGITS
     burden
    0.93
     Burden
    0.71
    burden
    0.71
     burdens
    0.69
     workload
    0.68
     부담
    0.65
     bande
    0.64
    s
    0.63
     monastery
    0.62
     weight
    0.59
    Activations Density 0.032%

    No Known Activations