© 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. 41-GEMMASCOPE-2-RES-262K
    7. 451
    Prev
    Next
    INDEX
    Explanations

    multi- prefix

    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_all/layer_41_width_262k_l0_big
    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
    ាតុ
    0.62
     thoſe
    0.60
    ួក
    0.57
    CHEMY
    0.57
    <unused202>
    0.57
     neutralizing
    0.55
    genCode
    0.55
    ઠળ
    0.55
    ្នែក
    0.55
    <unused706>
    0.55
    POSITIVE LOGITS
     Multi
    0.77
     multi
    0.71
     sclerosis
    0.71
     Mult
    0.70
    -
    0.68
    Multi
    0.67
     mult
    0.64
    k
    0.62
     myeloma
    0.61
    Discipl
    0.61
    Activations Density 0.013%

    No Known Activations