© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99054
    Prev
    Next
    INDEX
    Explanations

    metadata and code comments

    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
     aika
    -0.83
     conva
    -0.80
    大声
    -0.79
    啊啊
    -0.78
     устраи
    -0.77
    ại
    -0.77
     ранее
    -0.76
    eken
    -0.76
    šlo
    -0.76
    stuffs
    -0.75
    POSITIVE LOGITS
     fragte
    0.82
    vaná
    0.80
     Philos
    0.77
     reparation
    0.77
     комбина
    0.75
     ravioli
    0.75
     glaube
    0.75
     поэтому
    0.74
     unden
    0.74
    sipasi
    0.74
    Activations Density 0.042%

    No Known Activations