© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102332
    Prev
    Next
    INDEX
    Explanations

    saint names and places

    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
    i
    -2.16
     Their
    -2.08
     reemplazo
    -1.77
    旆
    -1.70
     Then
    -1.68
    </strong>
    -1.66
     estadía
    -1.64
    Allez
    -1.63
     amazing
    -1.62
    इटम
    -1.60
    POSITIVE LOGITS
    尼亚
    1.72
    astify
    1.63
     temperatura
    1.60
     varia
    1.57
     for
    1.56
    ")));
    1.55
    pherical
    1.53
     menú
    1.53
     roja
    1.52
     departament
    1.52
    Activations Density 0.005%

    No Known Activations