© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63148
    Prev
    Next
    INDEX
    Explanations

    XML encoding and content attributes

    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_34/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
     druh
    -0.94
     aasta
    -0.92
    digitalWrite
    -0.86
    🧠
    -0.82
    ElementException
    -0.81
     Lietu
    -0.81
    🅺
    -0.79
     BeautifulSoup
    -0.79
     LoggerFactory
    -0.77
    judicial
    -0.76
    POSITIVE LOGITS
    üsseldorf
    0.93
     móc
    0.85
     geliefert
    0.84
     Dox
    0.83
     interns
    0.79
     emu
    0.78
    owej
    0.78
    🪷
    0.77
     때문
    0.76
     gestellt
    0.75
    Activations Density 0.004%

    No Known Activations