© 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. 92496
    Prev
    Next
    INDEX
    Explanations

    in one go

    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
     something
    -1.06
    something
    -1.02
     things
    -0.99
    materi
    -0.84
     everything
    -0.83
     dingen
    -0.81
     SOMETHING
    -0.80
    Something
    -0.80
     iets
    -0.79
     Something
    -0.79
    POSITIVE LOGITS
     swoop
    1.57
     fell
    1.25
     sitting
    1.07
     convenient
    1.02
     glance
    0.95
    เดียว
    0.92
     go
    0.92
    fell
    0.91
     gulp
    0.91
     clump
    0.90
    Activations Density 0.050%

    No Known Activations