© 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. 108585
    Prev
    Next
    INDEX
    Explanations

    found something not available

    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
    zemu
    -1.09
     airpods
    -1.00
     verschillende
    -0.99
     diferite
    -0.97
    ragend
    -0.96
     différentes
    -0.95
     belangrijke
    -0.93
     várias
    -0.93
     asos
    -0.91
    varchar
    -0.90
    POSITIVE LOGITS
     suitable
    3.20
     подходя
    2.16
     available
    2.14
    suitable
    2.03
     affordable
    1.99
     adequate
    1.98
     decent
    1.90
     appropriate
    1.88
     Suitable
    1.79
    合适的
    1.78
    Activations Density 0.121%

    No Known Activations