© 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. 118450
    Prev
    Next
    INDEX
    Explanations

    `col`, `push`, `sigma`, `N`

    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
    なのかな
    -1.09
     توانید
    -1.00
    鏖
    -0.99
    Two
    -0.98
    なんだろう
    -0.96
    だよね
    -0.94
    魑
    -0.94
     تواند
    -0.90
     másik
    -0.90
    Sometimes
    -0.89
    POSITIVE LOGITS
     extremely
    1.23
     bizarre
    1.23
     amazingly
    1.23
     vastly
    1.22
     incredibly
    1.22
     remarkably
    1.20
     strikingly
    1.19
     quintessential
    1.16
     revered
    1.16
     dreadful
    1.16
    Activations Density 0.011%

    No Known Activations