© 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. 118221
    Prev
    Next
    INDEX
    Explanations

    specification

    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
    CloseOperation
    -0.87
     moelle
    -0.83
     césped
    -0.83
    运作
    -0.80
     restructuring
    -0.77
     restruct
    -0.77
     kelapa
    -0.77
    setw
    -0.75
     pertenecen
    -0.74
    Taken
    -0.73
    POSITIVE LOGITS
     specification
    3.84
     specifying
    3.66
     specify
    3.66
     specified
    3.38
     spec
    3.28
     specifications
    3.17
     Specification
    3.16
     Specify
    3.14
     specifies
    3.09
    specification
    2.94
    Activations Density 0.063%

    No Known Activations