© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118216
    Prev
    Next
    INDEX
    Explanations

    academic courses and study programmes

    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
     birçok
    -0.81
    Mesmo
    -0.78
     Holdings
    -0.78
    Opel
    -0.77
     przyczyn
    -0.77
     понимать
    -0.73
    測定
    -0.73
    所谓的
    -0.73
    TagHelper
    -0.71
    rían
    -0.71
    POSITIVE LOGITS
     modules
    1.10
     taught
    1.09
    studied
    1.00
     STUDY
    0.98
     your
    0.97
     духовке
    0.96
     studied
    0.94
     study
    0.90
     our
    0.89
    Study
    0.88
    Activations Density 0.018%

    No Known Activations