© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104906
    Prev
    Next
    INDEX
    Explanations

    an exercise 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
     \
    -1.88
     It
    -1.87
     The
    -1.80
     ‘
    -1.63
     “
    -1.55
     my
    -1.53
     sweetly
    -1.52
     peculiar
    -1.50
    {
    -1.48
     I
    -1.48
    POSITIVE LOGITS
    !”
    1.66
    According
    1.66
    ла
    1.65
    ції
    1.60
    weds
    1.59
    springen
    1.59
    šić
    1.58
     gik
    1.57
     fald
    1.56
    🎈
    1.56
    Activations Density 0.041%

    No Known Activations