© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1630
    Prev
    Next
    INDEX
    Explanations

    local establishments and services

    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
     ⓒ
    0.65
    oré
    0.63
     symbolizing
    0.63
     symbolize
    0.63
    署
    0.57
     slimming
    0.57
    ায়ার
    0.57
    Symbol
    0.56
    ,__
    0.56
     higiene
    0.55
    POSITIVE LOGITS
     brewery
    0.88
     Brewery
    0.78
     breweries
    0.74
     distillery
    0.70
     LPM
    0.70
     bourbon
    0.70
     Kubernetes
    0.69
     cid
    0.68
     kiddos
    0.67
    鮨
    0.66
    Activations Density 0.398%

    No Known Activations