© 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. 10-GEMMASCOPE-RES-131K
    7. 59055
    Prev
    Next
    INDEX
    Explanations

    Moodle, Odoo, Magento

    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
     burbu
    -2.02
     That
    -1.93
    旆
    -1.91
    𖥦
    -1.76
     invité
    -1.75
    轫
    -1.75
    =$?
    -1.74
    rdoba
    -1.72
     kağıdı
    -1.71
    訁
    -1.71
    POSITIVE LOGITS
    鱟
    2.02
    龊
    1.85
    ねば
    1.69
    ↵↵
    1.66
     dispuestos
    1.55
     哪些
    1.51
     _________
    1.47
     ”
    1.47
     aint
    1.45
    ’?
    1.44
    Activations Density 0.046%

    No Known Activations