© 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. 118134
    Prev
    Next
    INDEX
    Explanations

    controller or author code context

    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
     either
    -0.98
    camion
    -0.96
     Unterschied
    -0.93
     would
    -0.92
     as
    -0.90
     sufficient
    -0.90
    hhhhh
    -0.88
     sufficiently
    -0.85
     this
    -0.85
    +][
    -0.84
    POSITIVE LOGITS
    Admin
    1.19
     Admin
    1.18
     admin
    1.11
    Auth
    1.08
    admin
    1.04
     web
    1.00
     spa
    0.96
    Api
    0.94
     absolut
    0.93
     irr
    0.91
    Activations Density 0.005%

    No Known Activations