© 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. 99865
    Prev
    Next
    INDEX
    Explanations

    at this time

    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
     monstre
    -0.85
     collège
    -0.83
    ค์
    -0.81
     patrimoine
    -0.81
     mobilier
    -0.80
     剑
    -0.80
    Dónde
    -0.78
     Toscana
    -0.78
     lycée
    -0.78
     sark
    -0.76
    POSITIVE LOGITS
     moment
    2.36
     time
    1.92
     juncture
    1.59
    moment
    1.59
     Moment
    1.50
     present
    1.42
    Moment
    1.41
     writing
    1.27
     momento
    1.26
     Jun
    1.23
    Activations Density 0.012%

    No Known Activations