© 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. 9825
    Prev
    Next
    INDEX
    Explanations

    system calls and checks

    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
     bicicleta
    -1.52
    ggars
    -1.47
    贋
    -1.46
     estamp
    -1.42
     vidéos
    -1.36
     jugu
    -1.36
     inaugura
    -1.35
     consulté
    -1.35
     évé
    -1.34
    內容簡介
    -1.31
    POSITIVE LOGITS
    u
    1.50
     obicei
    1.37
    </em>
    1.31
    ro
    1.29
     Еще
    1.28
    z
    1.28
    r
    1.27
    </strong>
    1.27
    ino
    1.24
     queste
    1.23
    Activations Density 0.003%

    No Known Activations