© 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. 98547
    Prev
    Next
    INDEX
    Explanations

    introduces consequence

    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
     daardoor
    -1.52
     dabei
    -1.52
     ведь
    -1.45
     этом
    -1.43
     таком
    -1.42
     daarbij
    -1.39
    因為
    -1.33
    嗐
    -1.29
     cependant
    -1.26
    由于
    -1.20
    POSITIVE LOGITS
     instead
    2.09
     it
    1.92
     unless
    1.76
     when
    1.73
     whenever
    1.68
     we
    1.66
    もあって
    1.58
    instead
    1.48
    といって
    1.48
    Instead
    1.45
    Activations Density 0.063%

    No Known Activations