© 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. 66788
    Prev
    Next
    INDEX
    Explanations

    Our goal is

    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
     olje
    -1.16
     soyez
    -1.16
     guitarra
    -1.14
     that
    -1.13
    OGLE
    -1.09
     beren
    -1.09
    ográfico
    -1.05
    dekat
    -1.04
    xxi
    -1.04
     geef
    -1.02
    POSITIVE LOGITS
    ines
    1.22
    ö
    1.11
     etc
    1.04
    ate
    1.03
    ual
    1.02
    ans
    1.02
    ub
    1.02
    ise
    1.02
    te
    1.01
    ak
    1.01
    Activations Density 0.003%

    No Known Activations