© 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. 38872
    Prev
    Next
    INDEX
    Explanations

    present in or within

    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
    archiwizowane
    -2.25
    ’
    -2.13
    Външни
    -2.02
     présenter
    -2.00
    齮
    -1.98
    鲞
    -1.96
     kürzlich
    -1.92
     rafraî
    -1.89
    幛
    -1.86
     Dinas
    -1.85
    POSITIVE LOGITS
     in
    2.86
     Also
    1.84
     religiosas
    1.84
     ;
    1.82
    一方で
    1.79
     insists
    1.78
    .''
    1.77
    目的是
    1.77
     hijas
    1.77
     insufficient
    1.74
    Activations Density 0.017%

    No Known Activations