© 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. 11271
    Prev
    Next
    INDEX
    Explanations

    Q A format

    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
     Monfieur
    -2.48
     italia
    -2.45
     alip
    -2.39
     bahia
    -2.36
     milano
    -2.34
    !'
    -2.34
     These
    -2.33
    p
    -2.28
     sona
    -2.27
     hawa
    -2.23
    POSITIVE LOGITS
     you
    3.11
    鲀
    2.94
    </h4>
    2.52
    {
    2.48
     และ
    2.39
    箇所
    2.36
    蚨
    2.30
    了出来
    2.27
    跸
    2.25
    迓
    2.22
    Activations Density 0.000%

    No Known Activations