© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8840
    Prev
    Next
    INDEX
    Explanations

    URLs and directories

    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
     not
    -1.59
    龵
    -1.26
     один
    -1.22
    詼
    -1.22
     then
    -1.22
     pasaran
    -1.21
     サポート
    -1.20
    łem
    -1.18
     tasse
    -1.17
     otr
    -1.17
    POSITIVE LOGITS
    /
    1.55
    คือ
    1.41
    €™
    1.30
     nachts
    1.28
     وتم
    1.27
     ويمكن
    1.26
    有些不
    1.25
     sortir
    1.21
    msubsup
    1.20
     والتي
    1.20
    Activations Density 0.016%

    No Known Activations