© 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. 10-GEMMASCOPE-RES-131K
    7. 80764
    Prev
    Next
    INDEX
    Explanations

    years and months

    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_10/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
     …”
    -1.73
    èses
    -1.59
     lyd
    -1.48
    gingen
    -1.47
    cés
    -1.47
     fald
    -1.45
    pektive
    -1.44
    岿
    -1.41
     familie
    -1.39
     “…
    -1.39
    POSITIVE LOGITS
    (
    1.79
    </h1>
    1.75
     it
    1.73
    this
    1.73
    and
    1.73
    </h5>
    1.52
     of
    1.50
    、
    1.49
    tion
    1.47
    ki
    1.46
    Activations Density 0.065%

    No Known Activations