© 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. 84003
    Prev
    Next
    INDEX
    Explanations

    copyright or configuration files

    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
    infrastructure
    -0.80
     Holdings
    -0.79
    不住
    -0.77
     фар
    -0.74
    :[
    -0.73
    çük
    -0.73
    рит
    -0.72
    ingham
    -0.72
     Press
    -0.71
    execute
    -0.71
    POSITIVE LOGITS
     ceux
    0.88
    Irr
    0.84
    ēl
    0.79
     Darüber
    0.74
     amt
    0.73
     muſt
    0.73
     Lupin
    0.73
     Ceux
    0.73
     ARK
    0.73
    Ark
    0.73
    Activations Density 0.002%

    No Known Activations