© 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. 84573
    Prev
    Next
    INDEX
    Explanations

    options and alternatives

    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
    jshint
    -0.93
    äuser
    -0.90
     pediatric
    -0.88
     patriotic
    -0.85
     tourist
    -0.85
     ftate
    -0.84
    acknow
    -0.84
     cruelty
    -0.82
     fertility
    -0.82
     hairstyle
    -0.82
    POSITIVE LOGITS
     direct
    1.35
     alternatives
    1.34
     using
    1.33
     option
    1.27
     options
    1.15
    direct
    1.15
     manual
    1.14
     Direct
    1.09
     DIY
    1.06
    的方式
    1.05
    Activations Density 0.209%

    No Known Activations