© 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. 59308
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
     verschieden
    -0.88
     berbagai
    -0.86
     :)
    -0.84
     ZF
    -0.83
     ;)
    -0.79
     įva
    -0.79
    
    -0.77
    equipo
    -0.77
    inputText
    -0.77
    sequelize
    -0.76
    POSITIVE LOGITS
     com
    0.95
    com
    0.85
     Dot
    0.78
    Adic
    0.78
     dot
    0.75
     communities
    0.73
    𝐫
    0.73
    社區
    0.72
    new
    0.72
     لش
    0.72
    Activations Density 0.015%

    No Known Activations