© 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. 103260
    Prev
    Next
    INDEX
    Explanations

    credit lines and photo credits

    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
     bezeichneter
    -0.81
     companyId
    -0.79
    ĸ
    -0.77
     moun
    -0.76
     Tumors
    -0.75
    𝓿
    -0.75
    springer
    -0.73
     veloci
    -0.73
    Ո
    -0.73
    ések
    -0.71
    POSITIVE LOGITS
     action
    0.94
    Mandatory
    0.90
     Mandatory
    0.85
     USA
    0.84
     Action
    0.81
    Synd
    0.80
    Action
    0.77
    дьба
    0.77
     последова
    0.77
     sequence
    0.76
    Activations Density 0.035%

    No Known Activations