© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2403
    Prev
    Next
    INDEX
    Explanations

    stepping outside comfort zone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     什么
    1.91
     (\
    1.80
     这些
    1.78
     Со
    1.74
    的
    1.74
     学生
    1.73
    тического
    1.71
     处理
    1.70
    ع
    1.69
     नोएडा
    1.69
    POSITIVE LOGITS
     dessen
    1.68
    a
    1.59
     appunto
    1.57
     risulta
    1.44
    চ্ছিলেন
    1.42
     şekilde
    1.42
    aVal
    1.40
     justamente
    1.40
    চ্ছিলাম
    1.40
    $$_
    1.38
    Activations Density 0.329%

    No Known Activations