© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66470
    Prev
    Next
    INDEX
    Explanations

    academic journal and conference titles

    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_10/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
     یا
    -1.77
    ︕
    -1.70
    也沒
    -1.69
     huset
    -1.57
     enfance
    -1.56
    或
    -1.55
    鲧
    -1.55
    埽
    -1.55
    atürk
    -1.54
     этом
    -1.51
    POSITIVE LOGITS
     is
    1.83
     it
    1.57
    ↵
    1.52
    Recomendaciones
    1.49
     your
    1.47
     such
    1.45
     just
    1.37
    معرفی
    1.32
     frühen
    1.27
     which
    1.26
    Activations Density 0.026%

    No Known Activations