© 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. 102649
    Prev
    Next
    INDEX
    Explanations

    webpack and require

    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
     all
    -1.02
     well
    -0.99
     high
    -0.94
     additional
    -0.93
     very
    -0.88
     with
    -0.88
     even
    -0.86
     undoubtedly
    -0.85
     fairly
    -0.85
    Reaction
    -0.85
    POSITIVE LOGITS
    require
    0.98
     REQUIRE
    0.94
     sonhos
    0.93
    idig
    0.92
    Belgique
    0.89
     essas
    0.89
     大きい
    0.88
     adelant
    0.87
     desperdic
    0.87
     DAVID
    0.85
    Activations Density 0.001%

    No Known Activations