© 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. 22-GEMMASCOPE-RES-131K
    7. 34148
    Prev
    Next
    INDEX
    Explanations

    company and brand names

    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
     pierde
    -1.17
     Soit
    -1.16
    Ꮀ
    -1.04
     Aprove
    -1.03
     Wszyst
    -1.00
     немає
    -1.00
     Beaucoup
    -1.00
    conexao
    -0.99
     ЛИ
    -0.99
     Técnicas
    -0.98
    POSITIVE LOGITS
    ViewChild
    1.04
     detayl
    1.03
    становка
    1.00
    陇
    0.97
    First
    0.96
    ®
    0.95
     atracciones
    0.95
     müş
    0.91
    ΡΟ
    0.91
     проведе
    0.91
    Activations Density 0.033%

    No Known Activations