© 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. 98664
    Prev
    Next
    INDEX
    Explanations

    Taking Sides

    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
    سياسي
    -0.76
     зве
    -0.74
    Abraço
    -0.73
     هوا
    -0.71
    dessus
    -0.70
    Information
    -0.69
    lomer
    -0.69
    الر
    -0.69
    Abraços
    -0.69
    conservative
    -0.68
    POSITIVE LOGITS
    xel
    0.84
     PH
    0.82
    turo
    0.79
     angew
    0.79
     Socialist
    0.78
     Jacobian
    0.75
    kelas
    0.75
     الوا
    0.73
     Boeing
    0.73
     sneaker
    0.73
    Activations Density 0.022%

    No Known Activations