© 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. 99560
    Prev
    Next
    INDEX
    Explanations

    software licenses

    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
    硨
    -2.59
     About
    -2.55
    熥
    -2.53
     tournant
    -2.45
    を始め
    -2.39
    螄
    -2.38
     Of
    -2.31
     pleasures
    -2.30
     Brought
    -2.27
     jokingly
    -2.25
    POSITIVE LOGITS
    是個
    2.77
    Ꮉ
    2.38
    兩
    2.31
    
    2.30
    理会
    2.20
     nnd
    2.20
     読む
    2.19
    蜴
    2.19
     pastel
    2.17
    里有
    2.17
    Activations Density 0.096%

    No Known Activations