© 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. 22-GEMMASCOPE-RES-131K
    7. 35567
    Prev
    Next
    INDEX
    Explanations

    special characters like xe

    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
    темати
    -1.01
     fű
    -1.00
    accor
    -0.97
     می‌گو
    -0.96
     criaturas
    -0.96
    lowercase
    -0.96
     italiens
    -0.91
     potentiel
    -0.91
     sonora
    -0.89
     filme
    -0.89
    POSITIVE LOGITS
     riesce
    0.91
     şart
    0.86
     IBC
    0.86
     available
    0.85
     橋
    0.85
    ഃ
    0.84
    kmal
    0.84
    這種
    0.82
    ashion
    0.82
     Begriffe
    0.82
    Activations Density 0.001%

    No Known Activations