© 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. 8879
    Prev
    Next
    INDEX
    Explanations

    locations, institutions, and concepts

    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
     shoved
    -1.24
     Wartawan
    -1.23
     Ohne
    -1.23
     Variante
    -1.22
     Einige
    -1.19
     någon
    -1.16
     Warum
    -1.15
    浮现
    -1.12
    -“
    -1.10
    HasColumn
    -1.09
    POSITIVE LOGITS
    ↵↵↵
    1.49
     everything
    1.22
     Vorbild
    1.20
    chwitz
    1.20
    ENDIAN
    1.17
     kullanılan
    1.15
    jeron
    1.12
    ↵↵↵↵↵
    1.12
    ];
    1.10
    結束
    1.09
    Activations Density 0.189%

    No Known Activations