© 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. 85128
    Prev
    Next
    INDEX
    Explanations

    few [noun]

    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
    G
    -1.83
     such
    -1.73
     De
    -1.73
     Those
    -1.72
    C
    -1.65
    E
    -1.59
    H
    -1.59
    A
    -1.59
    {
    -1.57
     most
    -1.54
    POSITIVE LOGITS
    の上に
    1.77
    の前に
    1.76
     myös
    1.73
     $\{
    1.70
    Comme
    1.66
    ův
    1.66
    ferent
    1.63
    ൧
    1.63
     también
    1.63
     vaše
    1.62
    Activations Density 0.041%

    No Known Activations