© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90653
    Prev
    Next
    INDEX
    Explanations

    jumpers and circuit configurations

    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
    imenti
    -0.81
    ถึง
    -0.80
     Gebiete
    -0.75
     cafés
    -0.75
     Dewey
    -0.73
    imgUrl
    -0.70
    èlement
    -0.69
    getCollection
    -0.69
    小弟
    -0.68
     creato
    -0.68
    POSITIVE LOGITS
     jumpers
    2.70
     jumper
    2.66
     dip
    2.44
     DIP
    2.31
    DIP
    2.13
    jumper
    2.08
     Dip
    2.00
     Jumper
    1.99
     dips
    1.96
    Dip
    1.88
    Activations Density 0.032%

    No Known Activations