© 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. 34-GEMMASCOPE-RES-131K
    7. 587
    Prev
    Next
    INDEX
    Explanations

    file paths and configuration directories

    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
    colhead
    -0.80
    ynchrotron
    -0.78
     ස
    -0.76
    ம
    -0.74
    bés
    -0.74
    getBalance
    -0.73
     recic
    -0.73
    oterapia
    -0.72
    Microkernel
    -0.72
    жуть
    -0.71
    POSITIVE LOGITS
    ("/
    2.20
     "/
    2.17
     `/
    2.14
     /
    2.08
     '/
    2.06
    ('/
    1.92
    ="/
    1.70
     (/
    1.63
    "/
    1.56
    ='/
    1.48
    Activations Density 0.157%

    No Known Activations