© 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. 107493
    Prev
    Next
    INDEX
    Explanations

    numbered identifiers or labels

    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
     first
    -1.19
     two
    -1.17
     erste
    -1.02
     primeiro
    -0.94
     první
    -0.91
     three
    -0.89
     pixabay
    -0.88
    cą
    -0.86
     four
    -0.84
     zweier
    -0.84
    POSITIVE LOGITS
    第
    2.08
     第
    1.33
     numbered
    1.28
     №
    1.17
     #%
    1.13
    _{
    1.07
    ["
    1.04
    ={`
    0.96
     Episode
    0.93
    nth
    0.91
    Activations Density 0.025%

    No Known Activations