© 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. 12531
    Prev
    Next
    INDEX
    Explanations

    Columbian, cavernous, João

    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
     問
    -2.41
    {
    -2.38
    に
    -2.30
    お金
    -2.25
    愎
    -2.22
    produzione
    -2.22
     lidé
    -2.20
    秕
    -2.20
    >';
    -2.19
    緇
    -2.16
    POSITIVE LOGITS
    ’
    3.11
    ，“
    3.06
    ꔹ
    2.72
    u
    2.63
     encontrada
    2.61
    2
    2.52
    /
    2.45
     {
    2.39
    又在
    2.38
    </h3>
    2.33
    Activations Density 0.036%

    No Known Activations