© 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. 118440
    Prev
    Next
    INDEX
    Explanations

    wide variety and range

    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
     supposedly
    -0.99
     país
    -0.97
     very
    -0.97
    []{"
    -0.96
     fully
    -0.95
    さんです
    -0.94
     NATIONS
    -0.93
    heds
    -0.93
    リット
    -0.93
     really
    -0.91
    POSITIVE LOGITS
     range
    2.28
     variety
    1.81
     array
    1.60
     number
    1.52
     of
    1.41
     diversos
    1.25
     erila
    1.15
     myriad
    1.14
     diverses
    1.10
     slew
    1.09
    Activations Density 0.044%

    No Known Activations