© 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. 93103
    Prev
    Next
    INDEX
    Explanations

    historical periods and centuries

    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
     last
    -1.33
     today
    -1.30
     yesterday
    -1.26
     their
    -1.12
     October
    -1.10
     July
    -1.09
     at
    -1.05
     September
    -1.05
     November
    -1.03
     desde
    -0.99
    POSITIVE LOGITS
     começo
    1.27
     років
    1.22
     стене
    1.14
     enää
    1.14
    一些
    1.13
     frequent
    1.12
     Japão
    1.11
     increasingly
    1.10
     gradually
    1.07
     clube
    1.07
    Activations Density 0.057%

    No Known Activations