© 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. 79767
    Prev
    Next
    INDEX
    Explanations

    Adams Golf

    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
    അ
    -1.33
    ÁT
    -1.32
    jegy
    -1.29
    总之
    -1.29
    csak
    -1.26
    giène
    -1.25
     doar
    -1.23
    ebaran
    -1.21
    結構
    -1.20
     fiel
    -1.20
    POSITIVE LOGITS
     you
    1.73
     kemudian
    1.52
    すっ
    1.52
     envía
    1.50
     aprobó
    1.44
    。
    1.44
     reconoce
    1.43
     actualiza
    1.42
    !!!!!!!
    1.41
    他才
    1.41
    Activations Density 0.040%

    No Known Activations