© 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. 22-GEMMASCOPE-RES-131K
    7. 38959
    Prev
    Next
    INDEX
    Explanations

    import statements

    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_22/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
    request
    -0.89
     by
    -0.85
     toolStrip
    -0.83
    ੧
    -0.82
    oping
    -0.80
    REQUEST
    -0.79
    ਰ
    -0.79
    صد
    -0.79
    לק
    -0.77
     século
    -0.76
    POSITIVE LOGITS
     vårt
    1.01
     vår
    0.93
    æl
    0.90
    哌
    0.85
     våre
    0.84
    fillStyle
    0.81
     Це
    0.81
     Сам
    0.80
    Farma
    0.80
    韧
    0.79
    Activations Density 0.024%

    No Known Activations