© 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. 75095
    Prev
    Next
    INDEX
    Explanations

    constructor calls

    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
     kontakta
    -1.16
     település
    -1.14
     salonu
    -1.13
     sentirse
    -1.11
     comienzan
    -1.10
     daban
    -1.09
     pasará
    -1.08
     provocó
    -1.06
    ammlung
    -1.05
    ۲۰
    -1.05
    POSITIVE LOGITS
     what
    1.21
     for
    1.13
     könne
    1.09
     subtlety
    0.98
    ここで
    0.92
     Therefore
    0.91
     by
    0.90
    ecé
    0.90
    に行ってきました
    0.90
     températures
    0.88
    Activations Density 0.011%

    No Known Activations