© 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. 66310
    Prev
    Next
    INDEX
    Explanations

    times and dates

    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
     that
    -1.59
    parently
    -1.12
     розовый
    -1.05
     you
    -1.02
    诟
    -1.02
     групп
    -1.01
    −/−
    -0.99
     (
    -0.98
    bedingungen
    -0.96
    ：“……”
    -0.96
    POSITIVE LOGITS
     again
    1.24
     opět
    1.15
     великолеп
    1.05
     оригинала
    1.03
    odly
    1.00
    lidades
    0.98
     afternoon
    0.98
    螨
    0.97
     everlasting
    0.97
     liefde
    0.97
    Activations Density 0.004%

    No Known Activations