© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44277
    Prev
    Next
    INDEX
    Explanations

    correspondent reporter report

    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
    呖
    -1.93
     you
    -1.57
     gdy
    -1.44
     creencias
    -1.43
     quando
    -1.43
     atractivos
    -1.39
     sufficiently
    -1.38
     amables
    -1.35
     asistentes
    -1.28
    ());
    -1.27
    POSITIVE LOGITS
     `;
    1.49
     correspon
    1.38
     retorn
    1.28
    ate
    1.27
     impe
    1.25
     зависит
    1.24
     erros
    1.24
     excels
    1.23
     oportun
    1.22
     THOUGH
    1.22
    Activations Density 0.031%

    No Known Activations