© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48344
    Prev
    Next
    INDEX
    Explanations

    programming keywords and types

    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
    en
    -2.14
    _
    -2.14
    </h1>
    -1.99
    ner
    -1.89
    //
    -1.84
    y
    -1.84
    if
    -1.80
    ru
    -1.77
    r
    -1.76
    </th>
    -1.70
    POSITIVE LOGITS
     sentarse
    2.03
     soñar
    1.96
     juzgar
    1.84
     firmado
    1.81
    cetype
    1.76
     acercarse
    1.71
     entrenar
    1.69
     viajar
    1.67
    croix
    1.66
     escritores
    1.63
    Activations Density 0.008%

    No Known Activations