© 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. 21671
    Prev
    Next
    INDEX
    Explanations

    measurement units after in

    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
     comme
    -1.63
     très
    -1.61
     takie
    -1.59
     such
    -1.58
     not
    -1.54
    </td>
    -1.49
     头像
    -1.44
     aerolí
    -1.42
     cuatro
    -1.40
     metade
    -1.40
    POSITIVE LOGITS
    2
    1.45
    0
    1.37
     kroppen
    1.35
    的第一
    1.34
    oscopy
    1.34
     本店
    1.33
     interieur
    1.32
    mampuan
    1.30
     hvilken
    1.29
     to
    1.27
    Activations Density 0.035%

    No Known Activations