© 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. 84007
    Prev
    Next
    INDEX
    Explanations

    Hillary Clinton, North Carolina

    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
    حر
    -0.69
    لوم
    -0.67
    ytte
    -0.66
     globals
    -0.65
    Slope
    -0.64
    óa
    -0.63
     самом
    -0.63
    itized
    -0.62
     thôi
    -0.62
    Ciudad
    -0.62
    POSITIVE LOGITS
     template
    0.74
    SSSS
    0.71
    mise
    0.68
    াল
    0.67
     Alfaro
    0.67
    zzano
    0.65
    ilderness
    0.65
     Тем
    0.65
     lubang
    0.64
     Enroll
    0.64
    Activations Density 0.082%

    No Known Activations