© 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. 84093
    Prev
    Next
    INDEX
    Explanations

    modelmodels, responses, domain, generated

    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
    りました
    -0.84
     wybrać
    -0.79
     procedimento
    -0.75
     naquele
    -0.75
    了一個
    -0.73
     museums
    -0.73
     Mieter
    -0.71
    क्रम
    -0.71
     Development
    -0.70
     äusser
    -0.70
    POSITIVE LOGITS
     models
    1.49
    models
    1.48
    model
    1.47
    モデル
    1.33
     model
    1.32
     response
    1.29
    generated
    1.20
     responses
    1.19
    response
    1.17
     Models
    1.16
    Activations Density 0.038%

    No Known Activations