© 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. 109573
    Prev
    Next
    INDEX
    Explanations

    licensing and technical files

    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
     Ibarra
    -0.79
    🥏
    -0.78
    lahoma
    -0.78
     Pergamon
    -0.77
     procured
    -0.75
     receitas
    -0.75
     eleições
    -0.73
     Wally
    -0.73
    capai
    -0.73
    فين
    -0.72
    POSITIVE LOGITS
     Center
    0.68
     info
    0.66
    md
    0.66
    ⍵
    0.65
     Short
    0.65
     Driver
    0.65
    ast
    0.63
     находи
    0.61
    instein
    0.61
    ben
    0.60
    Activations Density 0.062%

    No Known Activations