© 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. 34-GEMMASCOPE-RES-131K
    7. 99142
    Prev
    Next
    INDEX
    Explanations

    software license headers

    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_34/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
     Captains
    -0.81
    ₣
    -0.78
    GAT
    -0.78
     Mujeres
    -0.74
     Siro
    -0.74
     Hecho
    -0.73
    满满
    -0.72
    hli
    -0.71
     Eraser
    -0.71
     heer
    -0.70
    POSITIVE LOGITS
     менять
    0.87
    ēju
    0.81
     pursues
    0.77
     voudrais
    0.77
    ];
    0.77
    llary
    0.75
     ασ
    0.75
    imi
    0.75
    logist
    0.74
     hiểu
    0.74
    Activations Density 0.608%

    No Known Activations