© 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. 110980
    Prev
    Next
    INDEX
    Explanations

    statistical significance

    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
    ijer
    -0.79
     ارد
    -0.69
     Apr
    -0.68
     كتاب
    -0.68
     Philippines
    -0.67
     sifat
    -0.67
    рий
    -0.64
     perros
    -0.64
     vestido
    -0.63
    Proposition
    -0.63
    POSITIVE LOGITS
     dib
    0.76
     Mlle
    0.70
    ături
    0.70
     Yaman
    0.68
     weep
    0.66
     รถ
    0.66
     Málaga
    0.65
     Tef
    0.65
    ABU
    0.65
     capri
    0.64
    Activations Density 0.054%

    No Known Activations