© 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. 84265
    Prev
    Next
    INDEX
    Explanations

    months in 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
    -1.92
     in
    -1.55
     how
    -1.40
     including
    -1.36
     had
    -1.34
     atau
    -1.33
     will
    -1.30
     можна
    -1.30
     has
    -1.30
     well
    -1.29
    POSITIVE LOGITS
     великолеп
    1.27
    を変える
    1.25
     [''],
    1.23
    拍了拍
    1.23
     provenant
    1.23
     различных
    1.22
     ſol
    1.20
    龊
    1.19
     junger
    1.18
    そうに
    1.18
    Activations Density 0.120%

    No Known Activations