© 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. 45541
    Prev
    Next
    INDEX
    Explanations

    template definition or assignment

    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
     cogn
    -0.72
    Sur
    -0.70
    rying
    -0.69
    IMEN
    -0.68
    ULE
    -0.68
    ried
    -0.67
    üy
    -0.67
    rité
    -0.66
    gelegen
    -0.66
    impl
    -0.66
    POSITIVE LOGITS
     acquired
    0.76
     adquirir
    0.73
     Acquired
    0.71
     clarity
    0.69
     achieved
    0.68
    oforte
    0.63
    Clarity
    0.63
    恥
    0.62
     sondern
    0.62
     acquisition
    0.62
    Activations Density 0.062%

    No Known Activations