© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2615
    Prev
    Next
    INDEX
    Explanations

    physical or emotional reactions

    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_13_width_65k_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
     পাকিস্তানের
    0.70
     पाकिस्तानी
    0.65
    婚
    0.65
    離婚
    0.65
    英國
    0.65
    日本
    0.63
     három
    0.63
    结婚
    0.63
     सऊदी
    0.62
    英国
    0.61
    POSITIVE LOGITS
     discre
    0.55
     recom
    0.53
     regain
    0.52
     recoup
    0.49
     reasonably
    0.48
     &/
    0.47
     Seesaw
    0.46
    ंटी
    0.46
     gratifying
    0.46
     તેમ
    0.45
    Activations Density 0.000%

    No Known Activations