© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31643
    Prev
    Next
    INDEX
    Explanations

    names and specific terms

    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
     strukt
    -0.80
     fotovolta
    -0.79
     twórc
    -0.78
     specifik
    -0.77
    Tv
    -0.77
     språk
    -0.75
    joyed
    -0.75
     rangement
    -0.75
    diam
    -0.74
    Converter
    -0.73
    POSITIVE LOGITS
    љено
    0.88
     glassware
    0.84
     ощущение
    0.82
     brauche
    0.78
    iten
    0.78
     utensils
    0.73
    这么
    0.73
     titer
    0.73
    有些人
    0.72
    正式
    0.71
    Activations Density 0.005%

    No Known Activations