© 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. 84020
    Prev
    Next
    INDEX
    Explanations

    puts things in or on

    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
     gdy
    -0.96
    olk
    -0.94
    être
    -0.91
    via
    -0.88
     durante
    -0.88
     pitä
    -0.88
     بن
    -0.86
     цене
    -0.86
    Via
    -0.85
     lorsqu
    -0.85
    POSITIVE LOGITS
     in
    2.55
     on
    1.98
     into
    1.92
     at
    1.46
     under
    1.38
     inline
    1.06
     offside
    1.05
    ไว้
    0.97
     underwater
    0.93
     навчання
    0.92
    Activations Density 0.031%

    No Known Activations