© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45402
    Prev
    Next
    INDEX
    Explanations

    years, riverdale, the cw, uptake, pre-

    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
    逕
    -0.77
     zune
    -0.74
     歳
    -0.73
     just
    -0.71
     Völker
    -0.71
     หลวง
    -0.71
    したり
    -0.71
     or
    -0.70
     LOL
    -0.69
     rodent
    -0.69
    POSITIVE LOGITS
     STAND
    0.87
     Figaro
    0.86
     Rumble
    0.85
    tamientos
    0.84
    Neon
    0.84
    ilerini
    0.83
     SUPPORT
    0.82
    alate
    0.81
    chanel
    0.79
     {
    
    
    0.79
    Activations Density 0.003%

    No Known Activations