© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201191
    Prev
    Next
    INDEX
    Explanations

    foreign scripts and concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    dark souls remastered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     disse
    0.44
     Eurovision
    0.43
     hai
    0.42
     Azerbaijan
    0.41
     han
    0.41
     kali
    0.41
     sut
    0.41
    裱
    0.41
    了很多
    0.40
     iki
    0.40
    POSITIVE LOGITS
    роид
    0.48
    üe
    0.46
     предоставляет
    0.46
     ننوت
    0.46
    樖
    0.46
    INESS
    0.45
    тной
    0.45
    эт
    0.45
     рабочей
    0.45
    INV
    0.44
    Activations Density 0.001%

    No Known Activations