© 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. 49334
    Prev
    Next
    INDEX
    Explanations

    magazine features and lists

    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
    ούμε
    -0.87
    湘南
    -0.83
    agreb
    -0.81
     slogans
    -0.79
    諳
    -0.77
    blogspot
    -0.77
    桡
    -0.75
    واس
    -0.71
    Они
    -0.71
     виро
    -0.71
    POSITIVE LOGITS
     Vog
    0.90
     Vogue
    0.89
    Vogue
    0.81
    выя
    0.78
     sujets
    0.74
    Legendary
    0.72
     仏
    0.71
     مقاله
    0.71
     šķ
    0.70
    مر
    0.69
    Activations Density 0.009%

    No Known Activations