© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 4882
    Prev
    Next
    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
     ${({
    0.81
    ভারতীয়
    0.81
    
    0.81
     conductance
    0.80
     noqa
    0.78
     dupatta
    0.76
    ExtensionsPath
    0.76
    ォ
    0.76
    汉语
    0.75
    etection
    0.75
    POSITIVE LOGITS
     Sarah
    1.12
     Richard
    1.11
     Sharma
    1.11
     Gary
    1.11
     Rebecca
    1.11
     Quinn
    1.10
     Gemma
    1.10
     Brian
    1.08
     Aaron
    1.08
     Kevin
    1.07
    Activations Density 0.509%

    No Known Activations