© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12853
    Prev
    Next
    INDEX
    Explanations

    visa and immigration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     we
    -1.68
     it
    -1.58
    ?
    -1.27
     our
    -1.25
    把它
    -1.23
    expandindo
    -1.21
     блюдо
    -1.20
    它
    -1.14
    歲
    -1.13
     dritten
    -1.11
    POSITIVE LOGITS
    ּוֹ
    1.82
     cinturón
    1.71
    וּ
    1.66
    ֶּ
    1.58
     ͜
    1.55
     lää
    1.52
     trámite
    1.50
     budete
    1.50
     immigration
    1.49
     fidèles
    1.48
    Activations Density 0.028%

    No Known Activations