© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30761
    Prev
    Next
    INDEX
    Explanations

    Korean names and companies

    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_34/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
     তারিখ
    -0.81
    LoadMore
    -0.75
     Spanish
    -0.74
     supplemental
    -0.72
    Perd
    -0.70
     grab
    -0.69
    ??
    -0.68
    罵
    -0.68
    用户信息
    -0.68
    ipzig
    -0.68
    POSITIVE LOGITS
     SST
    0.71
     Bry
    0.71
     vecteur
    0.69
     СИ
    0.68
    🇿
    0.67
    SST
    0.67
     Kelas
    0.67
    ťou
    0.67
    Condition
    0.66
    eon
    0.66
    Activations Density 0.031%

    No Known Activations